Google Colab Notebook experimenting with pre-trained CNN models available in PyTorch's torchvision library

pytorch-pretrained-models.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "pytorch-pretrained-models.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyNo+ca/7ZPPuodtov5q5Get",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "c6361b03ef6b4851a4994787bb41831d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_2e757051d55f4f37a33675a646755cea",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_c80d104d5cf445f49c08a6195973227d",
              "IPY_MODEL_3df5e0a746d643eba502045364c0b5d5"
            ]
          }
        },
        "2e757051d55f4f37a33675a646755cea": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c80d104d5cf445f49c08a6195973227d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_b9f89e7c7afe4f2b9bee1e791fbe3d4f",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 244418560,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 244418560,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_0ef1f33ceedb417896b674374d8bb743"
          }
        },
        "3df5e0a746d643eba502045364c0b5d5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_606b7c76165c4efc91c4d654e4d47d48",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 233M/233M [00:04<00:00, 58.4MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_1479c38de2c946938570cefc83bc5dc1"
          }
        },
        "b9f89e7c7afe4f2b9bee1e791fbe3d4f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "0ef1f33ceedb417896b674374d8bb743": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "606b7c76165c4efc91c4d654e4d47d48": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "1479c38de2c946938570cefc83bc5dc1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "6dc4c1039dbf4ae4ae2fbb0d739f0ce7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_6fd46c26d2ea4acbb83091b85fb2dfdd",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_602b0f77feb0479bb9b759b0811aee83",
              "IPY_MODEL_3d526d1345604ea79f99d7ded0a3cded"
            ]
          }
        },
        "6fd46c26d2ea4acbb83091b85fb2dfdd": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "602b0f77feb0479bb9b759b0811aee83": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_765f834d79ca4d15848c225f1f9818db",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 32342954,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 32342954,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_4212a5736e9e405b86efb2673af4ad47"
          }
        },
        "3d526d1345604ea79f99d7ded0a3cded": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_c06b7392a21742c284565dcb7073c8bb",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 30.8M/30.8M [00:00<00:00, 85.7MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_62a4d0e408684197a224949595b1d540"
          }
        },
        "765f834d79ca4d15848c225f1f9818db": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "4212a5736e9e405b86efb2673af4ad47": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c06b7392a21742c284565dcb7073c8bb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "62a4d0e408684197a224949595b1d540": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "396f39e3d51d4ee4a84f25c497fc6d17": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_f851aa8d63ff4e6dae645dfa310ace62",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_34efc8eb617b43a686ba94660f52d92a",
              "IPY_MODEL_2e2976a7bebd45e4909eec28477a55f3"
            ]
          }
        },
        "f851aa8d63ff4e6dae645dfa310ace62": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "34efc8eb617b43a686ba94660f52d92a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_ca966eb8685b4964b149e77cd2ff2c54",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 115730790,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 115730790,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_5ffc4a59df364cc2b8988b61ac717e45"
          }
        },
        "2e2976a7bebd45e4909eec28477a55f3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_7742b2e5b1924a71989c631d497be6d8",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 110M/110M [00:03<00:00, 38.4MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_27d4d9bb8a264650a509d0ef919a4645"
          }
        },
        "ca966eb8685b4964b149e77cd2ff2c54": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "5ffc4a59df364cc2b8988b61ac717e45": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7742b2e5b1924a71989c631d497be6d8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "27d4d9bb8a264650a509d0ef919a4645": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "e014bda09a974bb787a6018e46415a00": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_a81dc18628c14d9d945586d086e9c9b1",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_9f96515bb2a94dbdafa868705a2761da",
              "IPY_MODEL_ca9116a77d344f8e8faf31d323b29623"
            ]
          }
        },
        "a81dc18628c14d9d945586d086e9c9b1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9f96515bb2a94dbdafa868705a2761da": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_45995c78b290404e9d48fc929703c799",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 57365526,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 57365526,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_a13f28a9abc241118b9fb9cf45597ebc"
          }
        },
        "ca9116a77d344f8e8faf31d323b29623": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_1e097668bede46188e9b8d241dc2ac9f",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 54.7M/54.7M [00:01<00:00, 34.3MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_23fab0ecf725474eaa4709a63cb9646a"
          }
        },
        "45995c78b290404e9d48fc929703c799": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "a13f28a9abc241118b9fb9cf45597ebc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "1e097668bede46188e9b8d241dc2ac9f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "23fab0ecf725474eaa4709a63cb9646a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "d3a7b8b1334e4cdf89c7705be87b0e03": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_0e395046e13d4460aad8c77284f74c6e",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_c42c42b95b7c4ad3a6be9dbc6efc1bd8",
              "IPY_MODEL_bdf61dbf920a42d0adf7b656070a31e1"
            ]
          }
        },
        "0e395046e13d4460aad8c77284f74c6e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c42c42b95b7c4ad3a6be9dbc6efc1bd8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_7f8710079e28410a84bc155748caa460",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 81131730,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 81131730,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_bd31e7b9587549fb904178a33f722772"
          }
        },
        "bdf61dbf920a42d0adf7b656070a31e1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_c702cca2ee6a4978b7b145706f418b82",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 77.4M/77.4M [00:01<00:00, 67.2MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_62a71bedf6c3413f9c07cc9b27efd07b"
          }
        },
        "7f8710079e28410a84bc155748caa460": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "bd31e7b9587549fb904178a33f722772": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c702cca2ee6a4978b7b145706f418b82": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "62a71bedf6c3413f9c07cc9b27efd07b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "b403022ac58446c49722e34e42566681": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_faf0197c6b1345a0bb9b9894486b10c9",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_65f1b10860e84ad5baca355159bf5ce6",
              "IPY_MODEL_de06b57a9f334bbb8e0adac5ae070185"
            ]
          }
        },
        "faf0197c6b1345a0bb9b9894486b10c9": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "65f1b10860e84ad5baca355159bf5ce6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_d0629ab33afc4c65b5c837c2a03275e8",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 52147035,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 52147035,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_c30411ba1ec54248865469e489c7b123"
          }
        },
        "de06b57a9f334bbb8e0adac5ae070185": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_2a6152a358c94e2b90c312dcc40b1875",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 49.7M/49.7M [00:02<00:00, 22.9MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_0fb2b71101484287bcd58ff1c6bbd381"
          }
        },
        "d0629ab33afc4c65b5c837c2a03275e8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "c30411ba1ec54248865469e489c7b123": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2a6152a358c94e2b90c312dcc40b1875": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "0fb2b71101484287bcd58ff1c6bbd381": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9874a26fde894413b756b1cbe793808a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_f8537e061773446780e48bef79bd7153",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_9c78dcd8f278445f95f0a27d0385a16e",
              "IPY_MODEL_dfab2c269d7d45b89c8d51c51a6608be"
            ]
          }
        },
        "f8537e061773446780e48bef79bd7153": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9c78dcd8f278445f95f0a27d0385a16e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_04decccf0dd24344b7a5e0a44453cd0c",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 108857766,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 108857766,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_1baf4ea831944c4aac413e27c58de528"
          }
        },
        "dfab2c269d7d45b89c8d51c51a6608be": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_f805579834044b06b0475768500824d7",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 104M/104M [00:01<00:00, 85.7MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_155f43a677a54ae39bd56d3d99d5c917"
          }
        },
        "04decccf0dd24344b7a5e0a44453cd0c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "1baf4ea831944c4aac413e27c58de528": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f805579834044b06b0475768500824d7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "155f43a677a54ae39bd56d3d99d5c917": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7fca0776a8b246d9b67aef0a6ea37fed": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_2b529320757e4cc2978ab08f64efe413",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_63ff18f255774bb0ac5615b2cf92c1cf",
              "IPY_MODEL_7d437f2823984ffd868b3e99839360d6"
            ]
          }
        },
        "2b529320757e4cc2978ab08f64efe413": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "63ff18f255774bb0ac5615b2cf92c1cf": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_be320212a108401990c6cec8b8c11231",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 9008489,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 9008489,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_5b423f759dfd41bfa07e8743cca54583"
          }
        },
        "7d437f2823984ffd868b3e99839360d6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_2bca9101484e43258d110df6c38e23e2",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 8.59M/8.59M [00:00<00:00, 9.33MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_5bf2e449b1b14eb5a89feb15d05b8d53"
          }
        },
        "be320212a108401990c6cec8b8c11231": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "5b423f759dfd41bfa07e8743cca54583": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2bca9101484e43258d110df6c38e23e2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "5bf2e449b1b14eb5a89feb15d05b8d53": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9b2ce79d004f4789accd5ed7da959328": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_2cfd8c8358ef4eb1a17a6c5b3b904a42",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_1437d767bde6480bb8a99d2788974374",
              "IPY_MODEL_621106c13eee4544ab5cac601088c19c"
            ]
          }
        },
        "2cfd8c8358ef4eb1a17a6c5b3b904a42": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "1437d767bde6480bb8a99d2788974374": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_6f9631b56b574ec3b5d2b4b96765c07b",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 17736997,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 17736997,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_f4afa7c340914d38827276e1f5ba0524"
          }
        },
        "621106c13eee4544ab5cac601088c19c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_6bc926e7224c4428b470ba45f0247349",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 16.9M/16.9M [00:00<00:00, 17.8MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_f0e7aae29dc44a1aaa05a8991d1a1876"
          }
        },
        "6f9631b56b574ec3b5d2b4b96765c07b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "f4afa7c340914d38827276e1f5ba0524": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "6bc926e7224c4428b470ba45f0247349": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "f0e7aae29dc44a1aaa05a8991d1a1876": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "aebaa13f9f554895a3ebb1a6103cfc01": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_ccf98b834eb5474585e6263c251a3984",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_d61b586773d844f49123698c1aac70c3",
              "IPY_MODEL_e6f6be72fd2e4db9afd272d465b1c8be"
            ]
          }
        },
        "ccf98b834eb5474585e6263c251a3984": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "d61b586773d844f49123698c1aac70c3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_c1cc43a62e5e4e96b7d4f2aa0b9f9735",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 14212972,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 14212972,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_6b8650d111884e1ebd08e5e96f927a2e"
          }
        },
        "e6f6be72fd2e4db9afd272d465b1c8be": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_f13b49a5a5c548389d9ed959f9f527c6",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 13.6M/13.6M [00:00<00:00, 57.9MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_2aa00b597b42417681ed47bfe71c8b9d"
          }
        },
        "c1cc43a62e5e4e96b7d4f2aa0b9f9735": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "6b8650d111884e1ebd08e5e96f927a2e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f13b49a5a5c548389d9ed959f9f527c6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "2aa00b597b42417681ed47bfe71c8b9d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "1c507d6251a144d6881b378ee64320d9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_a54473eb65184d3cb25e84fa88b020e9",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_0216b02252134cfaa1e04bb9963b0e45",
              "IPY_MODEL_67e9938602154bbfb40db373c932df7e"
            ]
          }
        },
        "a54473eb65184d3cb25e84fa88b020e9": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "0216b02252134cfaa1e04bb9963b0e45": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_1e56f5cb39f345ad98c13dfe1f7a50bd",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 178728960,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 178728960,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_8a3ac5766ac24701aea02e407fd69167"
          }
        },
        "67e9938602154bbfb40db373c932df7e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_f8b09cb3da6c4cf9bd3bb9ccb01d6335",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 170M/170M [00:02<00:00, 62.4MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_d58f45588c704e56917baa3d6debb392"
          }
        },
        "1e56f5cb39f345ad98c13dfe1f7a50bd": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "8a3ac5766ac24701aea02e407fd69167": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f8b09cb3da6c4cf9bd3bb9ccb01d6335": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "d58f45588c704e56917baa3d6debb392": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ad6e240d1147486db85eda9432938bb6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_4ca8460410ac44459c39e374e3aa757c",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_9bdef02b07244da29c2bd44eff35f7f9",
              "IPY_MODEL_94e30ac4456546b0b0cc5fdbd718e7e0"
            ]
          }
        },
        "4ca8460410ac44459c39e374e3aa757c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9bdef02b07244da29c2bd44eff35f7f9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_b2a2203e777b4bffb39c2e74be63bc5c",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 241530880,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 241530880,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_03265a8d72d84e70b23b720e5036ba61"
          }
        },
        "94e30ac4456546b0b0cc5fdbd718e7e0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_7308fc1ce58a47e787f9125b7ee60121",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 230M/230M [00:03<00:00, 70.4MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_793d5c9c6574429e90789af57afd4da0"
          }
        },
        "b2a2203e777b4bffb39c2e74be63bc5c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "03265a8d72d84e70b23b720e5036ba61": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7308fc1ce58a47e787f9125b7ee60121": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "793d5c9c6574429e90789af57afd4da0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "a68d8c6ef5d04d88abd46eac69c9e214": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_029ac1036f824d14ade83d4288150cdf",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_015dd67d7ccf447aa88cd0a002b1c216",
              "IPY_MODEL_18f72c1fa0254ab1a342e93ff994bcfe"
            ]
          }
        },
        "029ac1036f824d14ade83d4288150cdf": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "015dd67d7ccf447aa88cd0a002b1c216": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_0388950a5dc346c484880c9f203f0b10",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 46827520,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 46827520,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_d34bb061997c48feb24b5a6ef96659ad"
          }
        },
        "18f72c1fa0254ab1a342e93ff994bcfe": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_7f0658578ca24c2c96f65a75321625f6",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 44.7M/44.7M [00:00<00:00, 144MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_d3aff64161a14afeaf88a3e86ea67d05"
          }
        },
        "0388950a5dc346c484880c9f203f0b10": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "d34bb061997c48feb24b5a6ef96659ad": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7f0658578ca24c2c96f65a75321625f6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "d3aff64161a14afeaf88a3e86ea67d05": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "90e3f1d4c77247359743f16e86293701": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_8b7079fd91eb475c9aab06b26f540456",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_cfe5b4e678f9495596e4ee17a968f055",
              "IPY_MODEL_1be42b2012534485be2c90533e86a367"
            ]
          }
        },
        "8b7079fd91eb475c9aab06b26f540456": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "cfe5b4e678f9495596e4ee17a968f055": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_d58c903a58c84ec4a7f3741c098d4ea8",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 87306240,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 87306240,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_625d90ff84864cc7a3e3f1d20f19fe95"
          }
        },
        "1be42b2012534485be2c90533e86a367": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_8d4be53aaf1f49d2850bbf956faeaa9c",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 83.3M/83.3M [00:01<00:00, 76.2MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_3d9ee211ce4d43f9a5d7ce48dc265bf0"
          }
        },
        "d58c903a58c84ec4a7f3741c098d4ea8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "625d90ff84864cc7a3e3f1d20f19fe95": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "8d4be53aaf1f49d2850bbf956faeaa9c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "3d9ee211ce4d43f9a5d7ce48dc265bf0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "91b640ac062a4f5db251b81ce727c16d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_ba928194f19743a898cfb8fce32092fb",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_0fb4e1f5bab04c4faf93a2039ddbb372",
              "IPY_MODEL_6f506f0cada44b52951edc3acd97112a"
            ]
          }
        },
        "ba928194f19743a898cfb8fce32092fb": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "0fb4e1f5bab04c4faf93a2039ddbb372": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_0e7f75c3c8fc4c70b901d7131152bfce",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 102502400,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 102502400,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_dd4e1351381241e0a154c68af1ca2dbf"
          }
        },
        "6f506f0cada44b52951edc3acd97112a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_0bc256bb7d634631953b50e37c58f323",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 97.8M/97.8M [00:01<00:00, 70.1MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_785d6d9c83914ce8920da27a74b4d5e4"
          }
        },
        "0e7f75c3c8fc4c70b901d7131152bfce": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "dd4e1351381241e0a154c68af1ca2dbf": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "0bc256bb7d634631953b50e37c58f323": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "785d6d9c83914ce8920da27a74b4d5e4": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "84d6c28ad92347988f71e2e196bed3c1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_d871c983a495483bb3f4dace73b5270a",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_4094bff304944bf2b484c10b8bca6998",
              "IPY_MODEL_dd99eccbb2f940e2ba739ce50b8d8d13"
            ]
          }
        },
        "d871c983a495483bb3f4dace73b5270a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "4094bff304944bf2b484c10b8bca6998": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_907be90d7b754694846e3aa9d19990cf",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 356082095,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 356082095,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_af696a41f8b54548b7473d25cf821c89"
          }
        },
        "dd99eccbb2f940e2ba739ce50b8d8d13": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_e16d6b42c25d48c5b33994ef5e622c74",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 340M/340M [00:08<00:00, 42.7MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_91887fa374e74b33a764e347497c466b"
          }
        },
        "907be90d7b754694846e3aa9d19990cf": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "af696a41f8b54548b7473d25cf821c89": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "e16d6b42c25d48c5b33994ef5e622c74": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "91887fa374e74b33a764e347497c466b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2f8bedfef9114709a422a88782c6b0ec": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_9f3ef1e74c11467fb34f7faf0371afe1",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_d9d2fb400104447682fa3bad8ce5c862",
              "IPY_MODEL_ea4c54f9e04942b3a0f2f52b457cff29"
            ]
          }
        },
        "9f3ef1e74c11467fb34f7faf0371afe1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "d9d2fb400104447682fa3bad8ce5c862": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_b9558451abf8441a8ddf600d93dc1980",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 100441675,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 100441675,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_6381cd56435d4c89bd82545e6330037b"
          }
        },
        "ea4c54f9e04942b3a0f2f52b457cff29": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_6f858b798de748c2a3f5714ff946b2a0",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 95.8M/95.8M [00:01<00:00, 91.6MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_a0ea566268464d60826a2b6f3e11bcc0"
          }
        },
        "b9558451abf8441a8ddf600d93dc1980": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "6381cd56435d4c89bd82545e6330037b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "6f858b798de748c2a3f5714ff946b2a0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "a0ea566268464d60826a2b6f3e11bcc0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "54c4a6cfa4bd44d2862b098116f5e123": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_175bec58935f4918952639b0f5289873",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_2d55af92e7d449df9a59fca33c0e693c",
              "IPY_MODEL_15571820c7f641ec8175b0833dea65a0"
            ]
          }
        },
        "175bec58935f4918952639b0f5289873": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2d55af92e7d449df9a59fca33c0e693c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_9da606aba5ee4c9fb43b0f80ddf9dba9",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 5538128,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 5538128,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_d77913295bfc4723955abca85ac00bdd"
          }
        },
        "15571820c7f641ec8175b0833dea65a0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_2cb12cbe047b452c83f4c196be430aef",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 5.28M/5.28M [00:02<00:00, 2.38MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_954ca28af09641e68106806118e2a944"
          }
        },
        "9da606aba5ee4c9fb43b0f80ddf9dba9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "d77913295bfc4723955abca85ac00bdd": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2cb12cbe047b452c83f4c196be430aef": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "954ca28af09641e68106806118e2a944": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "77ee33f3230641c4aba632c11659012b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_d511f5bdde46487b837da7d51f0c0732",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_f4c5daf2c5bf4920a27fffddd5ef497c",
              "IPY_MODEL_10acda15e172453e8d11b6f92856572e"
            ]
          }
        },
        "d511f5bdde46487b837da7d51f0c0732": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f4c5daf2c5bf4920a27fffddd5ef497c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_c19da5d2a7934e7a8724389b1c6746dc",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 9218294,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 9218294,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_214d344d6c674651905f78bc002931ec"
          }
        },
        "10acda15e172453e8d11b6f92856572e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_fd31aecccfc240f6b7cc02dd6a941bb8",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 8.79M/8.79M [00:00<00:00, 10.0MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_c8d469891ff04ef596e08e3503f0e17e"
          }
        },
        "c19da5d2a7934e7a8724389b1c6746dc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "214d344d6c674651905f78bc002931ec": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "fd31aecccfc240f6b7cc02dd6a941bb8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "c8d469891ff04ef596e08e3503f0e17e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "22c76c010ada4796a17ec358d5cbabf1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_662d68f38083475c9a72599f23b12e2d",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_8e7fb6d0f23a4a979e297f1653ba5a0e",
              "IPY_MODEL_6f6c87db7aa04c69a3805837a9e61ceb"
            ]
          }
        },
        "662d68f38083475c9a72599f23b12e2d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "8e7fb6d0f23a4a979e297f1653ba5a0e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_7de122ff854544db96a1fce800ca550d",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 5017600,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 5017600,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_3ed3aafac59b44399a901e8d23e8da22"
          }
        },
        "6f6c87db7aa04c69a3805837a9e61ceb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_27ca20b988dd45ab93999b80c6426dde",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 4.79M/4.79M [00:00<00:00, 41.9MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_cd7ecde3693c41668141ccad7cd5fb6d"
          }
        },
        "7de122ff854544db96a1fce800ca550d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "3ed3aafac59b44399a901e8d23e8da22": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "27ca20b988dd45ab93999b80c6426dde": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "cd7ecde3693c41668141ccad7cd5fb6d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "6edc8effb365460a83654a87165db51b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_4fbe433b94844429947f1988a8ff45ef",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_ff7c1fd5607d442eb7ffecd25ccfa38b",
              "IPY_MODEL_9b11d391df2f424194b4733d9c00c104"
            ]
          }
        },
        "4fbe433b94844429947f1988a8ff45ef": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ff7c1fd5607d442eb7ffecd25ccfa38b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_e05edaba29894298a1f2884c7ff01a09",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 4966400,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 4966400,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_24ae8bef43d44a429f480581b8e13612"
          }
        },
        "9b11d391df2f424194b4733d9c00c104": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_6c5b47f752b646f3b82ec73501acc7b3",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 4.74M/4.74M [01:51<00:00, 44.6kB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_392987e1e0194d7096f0a8e825ddf208"
          }
        },
        "e05edaba29894298a1f2884c7ff01a09": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "24ae8bef43d44a429f480581b8e13612": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "6c5b47f752b646f3b82ec73501acc7b3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "392987e1e0194d7096f0a8e825ddf208": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "8fa28af85f9343009de2c26215da520f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_728d5e00ac5c493d91aefbf271849b17",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_ea6ada2d9ed349aa853673ee5c78b251",
              "IPY_MODEL_0d6fb419300649e1b3809fc69e342c9a"
            ]
          }
        },
        "728d5e00ac5c493d91aefbf271849b17": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ea6ada2d9ed349aa853673ee5c78b251": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_93419331fad54b9a938e8cc432c39b8b",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 531456000,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 531456000,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_5789bc50e0884143bd70258fbf73c4bc"
          }
        },
        "0d6fb419300649e1b3809fc69e342c9a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_3781db1ae58e4f028adfb48164b79a5f",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 507M/507M [00:10<00:00, 50.7MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_1884dd9b299440a39f2514e4e96bc8fc"
          }
        },
        "93419331fad54b9a938e8cc432c39b8b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "5789bc50e0884143bd70258fbf73c4bc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "3781db1ae58e4f028adfb48164b79a5f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "1884dd9b299440a39f2514e4e96bc8fc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "bcc0434fd5d84995b760576605acacd4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_e05e268d4ea7462ab85ee1810d934150",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_5f4ff2e6eaec4bd39e3686cbfc7c1f50",
              "IPY_MODEL_45bc020d97b54b4f83dafd68b4cf9b0f"
            ]
          }
        },
        "e05e268d4ea7462ab85ee1810d934150": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "5f4ff2e6eaec4bd39e3686cbfc7c1f50": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_959fb04b15d44190bc5efbd5d4b271a0",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 531503671,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 531503671,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_6977514949d843abae787c5c4b625efc"
          }
        },
        "45bc020d97b54b4f83dafd68b4cf9b0f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_0ad5c86450ba497c8e1988c1bd97ae39",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 507M/507M [01:36<00:00, 5.49MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_cf09347172384a5e9453f052ef72c3f8"
          }
        },
        "959fb04b15d44190bc5efbd5d4b271a0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "6977514949d843abae787c5c4b625efc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "0ad5c86450ba497c8e1988c1bd97ae39": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "cf09347172384a5e9453f052ef72c3f8": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "dac203216d19459e9b117ed920890ce5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_473be6d01ffa41b5b3825e7db39241d1",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_76f174de6c4c4951b0e17e958fa2c88e",
              "IPY_MODEL_309458753a9a4a7b88ed4772de05bd3d"
            ]
          }
        },
        "473be6d01ffa41b5b3825e7db39241d1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "76f174de6c4c4951b0e17e958fa2c88e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_100ddd7b721849ad8e6a822ed5cdafa1",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 532194478,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 532194478,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_7dc5c0a9710048af855e03d53a19e03e"
          }
        },
        "309458753a9a4a7b88ed4772de05bd3d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_2e7a1bf3896c48388f0e26b89c4ebf19",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 508M/508M [01:29<00:00, 5.97MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_649ab62a53394c478a5711e761adccaa"
          }
        },
        "100ddd7b721849ad8e6a822ed5cdafa1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "7dc5c0a9710048af855e03d53a19e03e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2e7a1bf3896c48388f0e26b89c4ebf19": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "649ab62a53394c478a5711e761adccaa": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "5013293891244afb97f86774a4e6cd87": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_7e60ab3c53d44e5fb1cf440c0f9fa7f6",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_ae7fd733e7784969bce4b0ef1719c70a",
              "IPY_MODEL_4db7414bf4e7442cbab4e400f04f7b37"
            ]
          }
        },
        "7e60ab3c53d44e5fb1cf440c0f9fa7f6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ae7fd733e7784969bce4b0ef1719c70a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_8875b345971141989fc9042a1380fb84",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 532246301,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 532246301,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_14ba872fbb774a99ae50599346e8da8e"
          }
        },
        "4db7414bf4e7442cbab4e400f04f7b37": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_7b50af9f59f34d1cb4a7ccc19699451d",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 508M/508M [00:35<00:00, 15.1MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_8f5c75f0f252445388b1aacf78e8eb92"
          }
        },
        "8875b345971141989fc9042a1380fb84": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "14ba872fbb774a99ae50599346e8da8e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7b50af9f59f34d1cb4a7ccc19699451d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "8f5c75f0f252445388b1aacf78e8eb92": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "147979a7646f428fabc0fcdb3c112dcc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_0b9dfe3d04d744cca823671cc532e197",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_f36ff6aa4f6b428bab04083a81c4ff88",
              "IPY_MODEL_fe826a1670b448afb20c75a9137fbb22"
            ]
          }
        },
        "0b9dfe3d04d744cca823671cc532e197": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f36ff6aa4f6b428bab04083a81c4ff88": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_39a8efd90fcf40d9bb82c6c069555181",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 553433881,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 553433881,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_c0c8eae0ed7c428299000d4168df35ff"
          }
        },
        "fe826a1670b448afb20c75a9137fbb22": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_d49c41a09a794c5cbdb3eb387fa4db80",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 528M/528M [00:11<00:00, 46.3MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_f1432c3726a34c7b92dd7a900529096a"
          }
        },
        "39a8efd90fcf40d9bb82c6c069555181": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "c0c8eae0ed7c428299000d4168df35ff": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "d49c41a09a794c5cbdb3eb387fa4db80": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "f1432c3726a34c7b92dd7a900529096a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "bbd359dfe53a4870b1383c108c84c10c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_22398238ce224a2d930dd7d9df069a37",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_fafae8e470d5448980ac134bfbb51bfd",
              "IPY_MODEL_93963a854b9b42f58f5023fec5a4913f"
            ]
          }
        },
        "22398238ce224a2d930dd7d9df069a37": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "fafae8e470d5448980ac134bfbb51bfd": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_052267658ff544578892c15566c7db07",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 553507836,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 553507836,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_7a9bb55dd52148f0ad71f64eaf6638a3"
          }
        },
        "93963a854b9b42f58f5023fec5a4913f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_9e9be0fec4a54b819f5c7fd1bc0b5a07",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 528M/528M [00:02<00:00, 192MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_0475e6f9490044d2a7b0326ed77e24be"
          }
        },
        "052267658ff544578892c15566c7db07": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "7a9bb55dd52148f0ad71f64eaf6638a3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9e9be0fec4a54b819f5c7fd1bc0b5a07": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "0475e6f9490044d2a7b0326ed77e24be": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "86b7b99396bf451686dd0a2dd012b966": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_334d9785fbab458fb980adbca876f91e",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_97c1ecee31e04d2ebb01bb847421f6ee",
              "IPY_MODEL_31a6ddcdbb9e41ea91a91737b8befec9"
            ]
          }
        },
        "334d9785fbab458fb980adbca876f91e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "97c1ecee31e04d2ebb01bb847421f6ee": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_8cd6408a9e7a46abaad8d1079693a29f",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 574673361,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 574673361,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_f715017d0b824aba9f69bde74f5e5755"
          }
        },
        "31a6ddcdbb9e41ea91a91737b8befec9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_ef54fff2fdcc4ec88b5b7b633632a652",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 548M/548M [02:32<00:00, 3.76MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_e3efd202c8dc4ada82cb32166680e03e"
          }
        },
        "8cd6408a9e7a46abaad8d1079693a29f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "f715017d0b824aba9f69bde74f5e5755": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ef54fff2fdcc4ec88b5b7b633632a652": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "e3efd202c8dc4ada82cb32166680e03e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "e9a6a8d665664335b0fc494ec5638e8c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_541fbc391a64456ea2225e11fc7553cb",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_c4b575d70b4346a6b121f3bc0b5f3691",
              "IPY_MODEL_ab9305d65e3548889be323aa6517cf68"
            ]
          }
        },
        "541fbc391a64456ea2225e11fc7553cb": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c4b575d70b4346a6b121f3bc0b5f3691": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_b1dec07d3bd94700af9667b98ea042da",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 574769405,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 574769405,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_3d2d5bc1b8f94a459fea15e00d866424"
          }
        },
        "ab9305d65e3548889be323aa6517cf68": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_432e4652f7b346faad33a3d553023dca",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 548M/548M [00:06<00:00, 82.5MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_7f63c8ca1ec24415ba7339d5c885fee4"
          }
        },
        "b1dec07d3bd94700af9667b98ea042da": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "3d2d5bc1b8f94a459fea15e00d866424": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "432e4652f7b346faad33a3d553023dca": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "7f63c8ca1ec24415ba7339d5c885fee4": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "2e0b99245a25457f8dfb0660f1276a27": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_3d151e50159f466eafe5f6885b3ed5fb",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_5514bc667b43437a92ff2cf8e0a27bae",
              "IPY_MODEL_de3359c1274b450e84eac44d26af9838"
            ]
          }
        },
        "3d151e50159f466eafe5f6885b3ed5fb": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "5514bc667b43437a92ff2cf8e0a27bae": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_7a4965181e534a71ba3ca635ea97d6ae",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 254695146,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 254695146,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_716ee360aea74e2bb5a824883827a7e8"
          }
        },
        "de3359c1274b450e84eac44d26af9838": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_908455866afe4f94ab20f756f884bc8a",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 243M/243M [00:06<00:00, 40.5MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_f0275acbeef748ff863c8fbcecc41a47"
          }
        },
        "7a4965181e534a71ba3ca635ea97d6ae": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "716ee360aea74e2bb5a824883827a7e8": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "908455866afe4f94ab20f756f884bc8a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "f0275acbeef748ff863c8fbcecc41a47": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ebd913e2c0dd4933bdfdb6c29e4e5292": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_ff304475fe6b48e396fcb89186dcd0f8",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_f1a70c5c4a3d4b2b99ffe619a49612ce",
              "IPY_MODEL_99447a7722aa4f16a88c2b46060207cf"
            ]
          }
        },
        "ff304475fe6b48e396fcb89186dcd0f8": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "f1a70c5c4a3d4b2b99ffe619a49612ce": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_bac5f41d8da54bfdacccda2ee3d35b89",
            "_dom_classes": [],
            "description": "100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 138223492,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 138223492,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_2f372b0c50ff4438b85101999d0020ac"
          }
        },
        "99447a7722aa4f16a88c2b46060207cf": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_ded8b63f17294d248200d1467e8b0f53",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 132M/132M [00:03<00:00, 41.8MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_e602a7a31e634e1b93a747a896cfba44"
          }
        },
        "bac5f41d8da54bfdacccda2ee3d35b89": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "2f372b0c50ff4438b85101999d0020ac": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ded8b63f17294d248200d1467e8b0f53": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "e602a7a31e634e1b93a747a896cfba44": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/sakshamarora1/8828de7a46e2da78502b15813d80cfdf/pytorch-pretrained-models.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bYFSRxWphogr",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from __future__ import print_function, division\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.optim import lr_scheduler\n",
        "import torchvision\n",
        "from torchvision import datasets, models, transforms"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "z-0Fn3HKshtx",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000,
          "referenced_widgets": [
            "c6361b03ef6b4851a4994787bb41831d",
            "2e757051d55f4f37a33675a646755cea",
            "c80d104d5cf445f49c08a6195973227d",
            "3df5e0a746d643eba502045364c0b5d5",
            "b9f89e7c7afe4f2b9bee1e791fbe3d4f",
            "0ef1f33ceedb417896b674374d8bb743",
            "606b7c76165c4efc91c4d654e4d47d48",
            "1479c38de2c946938570cefc83bc5dc1",
            "6dc4c1039dbf4ae4ae2fbb0d739f0ce7",
            "6fd46c26d2ea4acbb83091b85fb2dfdd",
            "602b0f77feb0479bb9b759b0811aee83",
            "3d526d1345604ea79f99d7ded0a3cded",
            "765f834d79ca4d15848c225f1f9818db",
            "4212a5736e9e405b86efb2673af4ad47",
            "c06b7392a21742c284565dcb7073c8bb",
            "62a4d0e408684197a224949595b1d540",
            "396f39e3d51d4ee4a84f25c497fc6d17",
            "f851aa8d63ff4e6dae645dfa310ace62",
            "34efc8eb617b43a686ba94660f52d92a",
            "2e2976a7bebd45e4909eec28477a55f3",
            "ca966eb8685b4964b149e77cd2ff2c54",
            "5ffc4a59df364cc2b8988b61ac717e45",
            "7742b2e5b1924a71989c631d497be6d8",
            "27d4d9bb8a264650a509d0ef919a4645",
            "e014bda09a974bb787a6018e46415a00",
            "a81dc18628c14d9d945586d086e9c9b1",
            "9f96515bb2a94dbdafa868705a2761da",
            "ca9116a77d344f8e8faf31d323b29623",
            "45995c78b290404e9d48fc929703c799",
            "a13f28a9abc241118b9fb9cf45597ebc",
            "1e097668bede46188e9b8d241dc2ac9f",
            "23fab0ecf725474eaa4709a63cb9646a",
            "d3a7b8b1334e4cdf89c7705be87b0e03",
            "0e395046e13d4460aad8c77284f74c6e",
            "c42c42b95b7c4ad3a6be9dbc6efc1bd8",
            "bdf61dbf920a42d0adf7b656070a31e1",
            "7f8710079e28410a84bc155748caa460",
            "bd31e7b9587549fb904178a33f722772",
            "c702cca2ee6a4978b7b145706f418b82",
            "62a71bedf6c3413f9c07cc9b27efd07b",
            "b403022ac58446c49722e34e42566681",
            "faf0197c6b1345a0bb9b9894486b10c9",
            "65f1b10860e84ad5baca355159bf5ce6",
            "de06b57a9f334bbb8e0adac5ae070185",
            "d0629ab33afc4c65b5c837c2a03275e8",
            "c30411ba1ec54248865469e489c7b123",
            "2a6152a358c94e2b90c312dcc40b1875",
            "0fb2b71101484287bcd58ff1c6bbd381",
            "9874a26fde894413b756b1cbe793808a",
            "f8537e061773446780e48bef79bd7153",
            "9c78dcd8f278445f95f0a27d0385a16e",
            "dfab2c269d7d45b89c8d51c51a6608be",
            "04decccf0dd24344b7a5e0a44453cd0c",
            "1baf4ea831944c4aac413e27c58de528",
            "f805579834044b06b0475768500824d7",
            "155f43a677a54ae39bd56d3d99d5c917",
            "7fca0776a8b246d9b67aef0a6ea37fed",
            "2b529320757e4cc2978ab08f64efe413",
            "63ff18f255774bb0ac5615b2cf92c1cf",
            "7d437f2823984ffd868b3e99839360d6",
            "be320212a108401990c6cec8b8c11231",
            "5b423f759dfd41bfa07e8743cca54583",
            "2bca9101484e43258d110df6c38e23e2",
            "5bf2e449b1b14eb5a89feb15d05b8d53",
            "9b2ce79d004f4789accd5ed7da959328",
            "2cfd8c8358ef4eb1a17a6c5b3b904a42",
            "1437d767bde6480bb8a99d2788974374",
            "621106c13eee4544ab5cac601088c19c",
            "6f9631b56b574ec3b5d2b4b96765c07b",
            "f4afa7c340914d38827276e1f5ba0524",
            "6bc926e7224c4428b470ba45f0247349",
            "f0e7aae29dc44a1aaa05a8991d1a1876",
            "aebaa13f9f554895a3ebb1a6103cfc01",
            "ccf98b834eb5474585e6263c251a3984",
            "d61b586773d844f49123698c1aac70c3",
            "e6f6be72fd2e4db9afd272d465b1c8be",
            "c1cc43a62e5e4e96b7d4f2aa0b9f9735",
            "6b8650d111884e1ebd08e5e96f927a2e",
            "f13b49a5a5c548389d9ed959f9f527c6",
            "2aa00b597b42417681ed47bfe71c8b9d",
            "1c507d6251a144d6881b378ee64320d9",
            "a54473eb65184d3cb25e84fa88b020e9",
            "0216b02252134cfaa1e04bb9963b0e45",
            "67e9938602154bbfb40db373c932df7e",
            "1e56f5cb39f345ad98c13dfe1f7a50bd",
            "8a3ac5766ac24701aea02e407fd69167",
            "f8b09cb3da6c4cf9bd3bb9ccb01d6335",
            "d58f45588c704e56917baa3d6debb392",
            "ad6e240d1147486db85eda9432938bb6",
            "4ca8460410ac44459c39e374e3aa757c",
            "9bdef02b07244da29c2bd44eff35f7f9",
            "94e30ac4456546b0b0cc5fdbd718e7e0",
            "b2a2203e777b4bffb39c2e74be63bc5c",
            "03265a8d72d84e70b23b720e5036ba61",
            "7308fc1ce58a47e787f9125b7ee60121",
            "793d5c9c6574429e90789af57afd4da0",
            "a68d8c6ef5d04d88abd46eac69c9e214",
            "029ac1036f824d14ade83d4288150cdf",
            "015dd67d7ccf447aa88cd0a002b1c216",
            "18f72c1fa0254ab1a342e93ff994bcfe",
            "0388950a5dc346c484880c9f203f0b10",
            "d34bb061997c48feb24b5a6ef96659ad",
            "7f0658578ca24c2c96f65a75321625f6",
            "d3aff64161a14afeaf88a3e86ea67d05",
            "90e3f1d4c77247359743f16e86293701",
            "8b7079fd91eb475c9aab06b26f540456",
            "cfe5b4e678f9495596e4ee17a968f055",
            "1be42b2012534485be2c90533e86a367",
            "d58c903a58c84ec4a7f3741c098d4ea8",
            "625d90ff84864cc7a3e3f1d20f19fe95",
            "8d4be53aaf1f49d2850bbf956faeaa9c",
            "3d9ee211ce4d43f9a5d7ce48dc265bf0",
            "91b640ac062a4f5db251b81ce727c16d",
            "ba928194f19743a898cfb8fce32092fb",
            "0fb4e1f5bab04c4faf93a2039ddbb372",
            "6f506f0cada44b52951edc3acd97112a",
            "0e7f75c3c8fc4c70b901d7131152bfce",
            "dd4e1351381241e0a154c68af1ca2dbf",
            "0bc256bb7d634631953b50e37c58f323",
            "785d6d9c83914ce8920da27a74b4d5e4",
            "84d6c28ad92347988f71e2e196bed3c1",
            "d871c983a495483bb3f4dace73b5270a",
            "4094bff304944bf2b484c10b8bca6998",
            "dd99eccbb2f940e2ba739ce50b8d8d13",
            "907be90d7b754694846e3aa9d19990cf",
            "af696a41f8b54548b7473d25cf821c89",
            "e16d6b42c25d48c5b33994ef5e622c74",
            "91887fa374e74b33a764e347497c466b",
            "2f8bedfef9114709a422a88782c6b0ec",
            "9f3ef1e74c11467fb34f7faf0371afe1",
            "d9d2fb400104447682fa3bad8ce5c862",
            "ea4c54f9e04942b3a0f2f52b457cff29",
            "b9558451abf8441a8ddf600d93dc1980",
            "6381cd56435d4c89bd82545e6330037b",
            "6f858b798de748c2a3f5714ff946b2a0",
            "a0ea566268464d60826a2b6f3e11bcc0",
            "54c4a6cfa4bd44d2862b098116f5e123",
            "175bec58935f4918952639b0f5289873",
            "2d55af92e7d449df9a59fca33c0e693c",
            "15571820c7f641ec8175b0833dea65a0",
            "9da606aba5ee4c9fb43b0f80ddf9dba9",
            "d77913295bfc4723955abca85ac00bdd",
            "2cb12cbe047b452c83f4c196be430aef",
            "954ca28af09641e68106806118e2a944",
            "77ee33f3230641c4aba632c11659012b",
            "d511f5bdde46487b837da7d51f0c0732",
            "f4c5daf2c5bf4920a27fffddd5ef497c",
            "10acda15e172453e8d11b6f92856572e",
            "c19da5d2a7934e7a8724389b1c6746dc",
            "214d344d6c674651905f78bc002931ec",
            "fd31aecccfc240f6b7cc02dd6a941bb8",
            "c8d469891ff04ef596e08e3503f0e17e",
            "22c76c010ada4796a17ec358d5cbabf1",
            "662d68f38083475c9a72599f23b12e2d",
            "8e7fb6d0f23a4a979e297f1653ba5a0e",
            "6f6c87db7aa04c69a3805837a9e61ceb",
            "7de122ff854544db96a1fce800ca550d",
            "3ed3aafac59b44399a901e8d23e8da22",
            "27ca20b988dd45ab93999b80c6426dde",
            "cd7ecde3693c41668141ccad7cd5fb6d",
            "6edc8effb365460a83654a87165db51b",
            "4fbe433b94844429947f1988a8ff45ef",
            "ff7c1fd5607d442eb7ffecd25ccfa38b",
            "9b11d391df2f424194b4733d9c00c104",
            "e05edaba29894298a1f2884c7ff01a09",
            "24ae8bef43d44a429f480581b8e13612",
            "6c5b47f752b646f3b82ec73501acc7b3",
            "392987e1e0194d7096f0a8e825ddf208",
            "8fa28af85f9343009de2c26215da520f",
            "728d5e00ac5c493d91aefbf271849b17",
            "ea6ada2d9ed349aa853673ee5c78b251",
            "0d6fb419300649e1b3809fc69e342c9a",
            "93419331fad54b9a938e8cc432c39b8b",
            "5789bc50e0884143bd70258fbf73c4bc",
            "3781db1ae58e4f028adfb48164b79a5f",
            "1884dd9b299440a39f2514e4e96bc8fc",
            "bcc0434fd5d84995b760576605acacd4",
            "e05e268d4ea7462ab85ee1810d934150",
            "5f4ff2e6eaec4bd39e3686cbfc7c1f50",
            "45bc020d97b54b4f83dafd68b4cf9b0f",
            "959fb04b15d44190bc5efbd5d4b271a0",
            "6977514949d843abae787c5c4b625efc",
            "0ad5c86450ba497c8e1988c1bd97ae39",
            "cf09347172384a5e9453f052ef72c3f8",
            "dac203216d19459e9b117ed920890ce5",
            "473be6d01ffa41b5b3825e7db39241d1",
            "76f174de6c4c4951b0e17e958fa2c88e",
            "309458753a9a4a7b88ed4772de05bd3d",
            "100ddd7b721849ad8e6a822ed5cdafa1",
            "7dc5c0a9710048af855e03d53a19e03e",
            "2e7a1bf3896c48388f0e26b89c4ebf19",
            "649ab62a53394c478a5711e761adccaa",
            "5013293891244afb97f86774a4e6cd87",
            "7e60ab3c53d44e5fb1cf440c0f9fa7f6",
            "ae7fd733e7784969bce4b0ef1719c70a",
            "4db7414bf4e7442cbab4e400f04f7b37",
            "8875b345971141989fc9042a1380fb84",
            "14ba872fbb774a99ae50599346e8da8e",
            "7b50af9f59f34d1cb4a7ccc19699451d",
            "8f5c75f0f252445388b1aacf78e8eb92",
            "147979a7646f428fabc0fcdb3c112dcc",
            "0b9dfe3d04d744cca823671cc532e197",
            "f36ff6aa4f6b428bab04083a81c4ff88",
            "fe826a1670b448afb20c75a9137fbb22",
            "39a8efd90fcf40d9bb82c6c069555181",
            "c0c8eae0ed7c428299000d4168df35ff",
            "d49c41a09a794c5cbdb3eb387fa4db80",
            "f1432c3726a34c7b92dd7a900529096a",
            "bbd359dfe53a4870b1383c108c84c10c",
            "22398238ce224a2d930dd7d9df069a37",
            "fafae8e470d5448980ac134bfbb51bfd",
            "93963a854b9b42f58f5023fec5a4913f",
            "052267658ff544578892c15566c7db07",
            "7a9bb55dd52148f0ad71f64eaf6638a3",
            "9e9be0fec4a54b819f5c7fd1bc0b5a07",
            "0475e6f9490044d2a7b0326ed77e24be",
            "86b7b99396bf451686dd0a2dd012b966",
            "334d9785fbab458fb980adbca876f91e",
            "97c1ecee31e04d2ebb01bb847421f6ee",
            "31a6ddcdbb9e41ea91a91737b8befec9",
            "8cd6408a9e7a46abaad8d1079693a29f",
            "f715017d0b824aba9f69bde74f5e5755",
            "ef54fff2fdcc4ec88b5b7b633632a652",
            "e3efd202c8dc4ada82cb32166680e03e",
            "e9a6a8d665664335b0fc494ec5638e8c",
            "541fbc391a64456ea2225e11fc7553cb",
            "c4b575d70b4346a6b121f3bc0b5f3691",
            "ab9305d65e3548889be323aa6517cf68",
            "b1dec07d3bd94700af9667b98ea042da",
            "3d2d5bc1b8f94a459fea15e00d866424",
            "432e4652f7b346faad33a3d553023dca",
            "7f63c8ca1ec24415ba7339d5c885fee4",
            "2e0b99245a25457f8dfb0660f1276a27",
            "3d151e50159f466eafe5f6885b3ed5fb",
            "5514bc667b43437a92ff2cf8e0a27bae",
            "de3359c1274b450e84eac44d26af9838",
            "7a4965181e534a71ba3ca635ea97d6ae",
            "716ee360aea74e2bb5a824883827a7e8",
            "908455866afe4f94ab20f756f884bc8a",
            "f0275acbeef748ff863c8fbcecc41a47",
            "ebd913e2c0dd4933bdfdb6c29e4e5292",
            "ff304475fe6b48e396fcb89186dcd0f8",
            "f1a70c5c4a3d4b2b99ffe619a49612ce",
            "99447a7722aa4f16a88c2b46060207cf",
            "bac5f41d8da54bfdacccda2ee3d35b89",
            "2f372b0c50ff4438b85101999d0020ac",
            "ded8b63f17294d248200d1467e8b0f53",
            "e602a7a31e634e1b93a747a896cfba44"
          ]
        },
        "outputId": "bfa800dc-544a-4333-d574-e0eb948b7887"
      },
      "source": [
        "model_list = []\n",
        "for model in dir(models):\n",
        "    if model[0].islower():\n",
        "        if hasattr(getattr(models, model), '__call__'):\n",
        "            print(f\"Loading Pretrained Model: {model}\")\n",
        "            try:\n",
        "                model_list.append((model, getattr(models, model)(pretrained=True)))\n",
        "            except:\n",
        "                print(\"Download failed!\")\n",
        "                print(f\"No checkpoint is available for model: {model}\\n\")\n",
        "                "
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Loading Pretrained Model: alexnet\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/alexnet-owt-4df8aa71.pth\" to /root/.cache/torch/hub/checkpoints/alexnet-owt-4df8aa71.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "c6361b03ef6b4851a4994787bb41831d",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=244418560.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: densenet121\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/densenet121-a639ec97.pth\" to /root/.cache/torch/hub/checkpoints/densenet121-a639ec97.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "6dc4c1039dbf4ae4ae2fbb0d739f0ce7",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=32342954.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: densenet161\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/densenet161-8d451a50.pth\" to /root/.cache/torch/hub/checkpoints/densenet161-8d451a50.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "396f39e3d51d4ee4a84f25c497fc6d17",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=115730790.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: densenet169\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/densenet169-b2777c0a.pth\" to /root/.cache/torch/hub/checkpoints/densenet169-b2777c0a.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "e014bda09a974bb787a6018e46415a00",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=57365526.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: densenet201\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/densenet201-c1103571.pth\" to /root/.cache/torch/hub/checkpoints/densenet201-c1103571.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "d3a7b8b1334e4cdf89c7705be87b0e03",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=81131730.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: googlenet\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/googlenet-1378be20.pth\" to /root/.cache/torch/hub/checkpoints/googlenet-1378be20.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "b403022ac58446c49722e34e42566681",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=52147035.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: inception_v3\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/inception_v3_google-1a9a5a14.pth\" to /root/.cache/torch/hub/checkpoints/inception_v3_google-1a9a5a14.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "9874a26fde894413b756b1cbe793808a",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=108857766.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: mnasnet0_5\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/mnasnet0.5_top1_67.823-3ffadce67e.pth\" to /root/.cache/torch/hub/checkpoints/mnasnet0.5_top1_67.823-3ffadce67e.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "7fca0776a8b246d9b67aef0a6ea37fed",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=9008489.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: mnasnet0_75\n",
            "Download failed!\n",
            "No checkpoint is available for model: mnasnet0_75\n",
            "\n",
            "Loading Pretrained Model: mnasnet1_0\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/mnasnet1.0_top1_73.512-f206786ef8.pth\" to /root/.cache/torch/hub/checkpoints/mnasnet1.0_top1_73.512-f206786ef8.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "9b2ce79d004f4789accd5ed7da959328",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=17736997.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: mnasnet1_3\n",
            "Download failed!\n",
            "No checkpoint is available for model: mnasnet1_3\n",
            "\n",
            "Loading Pretrained Model: mobilenet_v2\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/mobilenet_v2-b0353104.pth\" to /root/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "aebaa13f9f554895a3ebb1a6103cfc01",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=14212972.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnet101\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnet101-5d3b4d8f.pth\" to /root/.cache/torch/hub/checkpoints/resnet101-5d3b4d8f.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "1c507d6251a144d6881b378ee64320d9",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=178728960.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnet152\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnet152-b121ed2d.pth\" to /root/.cache/torch/hub/checkpoints/resnet152-b121ed2d.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "ad6e240d1147486db85eda9432938bb6",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=241530880.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnet18\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnet18-5c106cde.pth\" to /root/.cache/torch/hub/checkpoints/resnet18-5c106cde.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "a68d8c6ef5d04d88abd46eac69c9e214",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=46827520.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnet34\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnet34-333f7ec4.pth\" to /root/.cache/torch/hub/checkpoints/resnet34-333f7ec4.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "90e3f1d4c77247359743f16e86293701",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=87306240.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnet50\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnet50-19c8e357.pth\" to /root/.cache/torch/hub/checkpoints/resnet50-19c8e357.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "91b640ac062a4f5db251b81ce727c16d",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=102502400.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnext101_32x8d\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth\" to /root/.cache/torch/hub/checkpoints/resnext101_32x8d-8ba56ff5.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "84d6c28ad92347988f71e2e196bed3c1",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=356082095.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: resnext50_32x4d\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth\" to /root/.cache/torch/hub/checkpoints/resnext50_32x4d-7cdf4587.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "2f8bedfef9114709a422a88782c6b0ec",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=100441675.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: shufflenet_v2_x0_5\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/shufflenetv2_x0.5-f707e7126e.pth\" to /root/.cache/torch/hub/checkpoints/shufflenetv2_x0.5-f707e7126e.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "54c4a6cfa4bd44d2862b098116f5e123",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=5538128.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: shufflenet_v2_x1_0\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/shufflenetv2_x1-5666bf0f80.pth\" to /root/.cache/torch/hub/checkpoints/shufflenetv2_x1-5666bf0f80.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "77ee33f3230641c4aba632c11659012b",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=9218294.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: shufflenet_v2_x1_5\n",
            "Download failed!\n",
            "No checkpoint is available for model: shufflenet_v2_x1_5\n",
            "\n",
            "Loading Pretrained Model: shufflenet_v2_x2_0\n",
            "Download failed!\n",
            "No checkpoint is available for model: shufflenet_v2_x2_0\n",
            "\n",
            "Loading Pretrained Model: squeezenet1_0\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/squeezenet1_0-a815701f.pth\" to /root/.cache/torch/hub/checkpoints/squeezenet1_0-a815701f.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "22c76c010ada4796a17ec358d5cbabf1",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=5017600.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/squeezenet1_1-f364aa15.pth\" to /root/.cache/torch/hub/checkpoints/squeezenet1_1-f364aa15.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: squeezenet1_1\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "6edc8effb365460a83654a87165db51b",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=4966400.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg11\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg11-bbd30ac9.pth\" to /root/.cache/torch/hub/checkpoints/vgg11-bbd30ac9.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "8fa28af85f9343009de2c26215da520f",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=531456000.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg11_bn\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg11_bn-6002323d.pth\" to /root/.cache/torch/hub/checkpoints/vgg11_bn-6002323d.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "bcc0434fd5d84995b760576605acacd4",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=531503671.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg13\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg13-c768596a.pth\" to /root/.cache/torch/hub/checkpoints/vgg13-c768596a.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "dac203216d19459e9b117ed920890ce5",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=532194478.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg13_bn\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg13_bn-abd245e5.pth\" to /root/.cache/torch/hub/checkpoints/vgg13_bn-abd245e5.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "5013293891244afb97f86774a4e6cd87",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=532246301.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg16\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg16-397923af.pth\" to /root/.cache/torch/hub/checkpoints/vgg16-397923af.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "147979a7646f428fabc0fcdb3c112dcc",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=553433881.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg16_bn\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg16_bn-6c64b313.pth\" to /root/.cache/torch/hub/checkpoints/vgg16_bn-6c64b313.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "bbd359dfe53a4870b1383c108c84c10c",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=553507836.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg19\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg19-dcbb9e9d.pth\" to /root/.cache/torch/hub/checkpoints/vgg19-dcbb9e9d.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "86b7b99396bf451686dd0a2dd012b966",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=574673361.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: vgg19_bn\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/vgg19_bn-c79401a0.pth\" to /root/.cache/torch/hub/checkpoints/vgg19_bn-c79401a0.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "e9a6a8d665664335b0fc494ec5638e8c",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=574769405.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: wide_resnet101_2\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth\" to /root/.cache/torch/hub/checkpoints/wide_resnet101_2-32ee1156.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "2e0b99245a25457f8dfb0660f1276a27",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=254695146.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Loading Pretrained Model: wide_resnet50_2\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading: \"https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth\" to /root/.cache/torch/hub/checkpoints/wide_resnet50_2-95faca4d.pth\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "ebd913e2c0dd4933bdfdb6c29e4e5292",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, max=138223492.0), HTML(value='')))"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7AUHUUeF982L",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "28af1f62-2b2a-4542-afe9-14e85b8f92ce"
      },
      "source": [
        "len(model_list)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "31"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DWSUtZHg-at1",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "c355549b-3087-425f-ec7a-00c367bfea2a"
      },
      "source": [
        "for model_name, model in model_list:\n",
        "    print(\"=================================== \" + model_name + \" ===================================\")\n",
        "    print(model, \"\\n\\n\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "=================================== alexnet ===================================\n",
            "AlexNet(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (7): ReLU(inplace=True)\n",
            "    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (9): ReLU(inplace=True)\n",
            "    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): ReLU(inplace=True)\n",
            "    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))\n",
            "  (classifier): Sequential(\n",
            "    (0): Dropout(p=0.5, inplace=False)\n",
            "    (1): Linear(in_features=9216, out_features=4096, bias=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): Dropout(p=0.5, inplace=False)\n",
            "    (4): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (5): ReLU(inplace=True)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== densenet121 ===================================\n",
            "DenseNet(\n",
            "  (features): Sequential(\n",
            "    (conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "    (norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (relu0): ReLU(inplace=True)\n",
            "    (pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "    (denseblock1): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition1): _Transition(\n",
            "      (norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock2): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition2): _Transition(\n",
            "      (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock3): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition3): _Transition(\n",
            "      (norm): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock4): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (norm5): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (classifier): Linear(in_features=1024, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== densenet161 ===================================\n",
            "DenseNet(\n",
            "  (features): Sequential(\n",
            "    (conv0): Conv2d(3, 96, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "    (norm0): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (relu0): ReLU(inplace=True)\n",
            "    (pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "    (denseblock1): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(96, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(144, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(240, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(336, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(336, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition1): _Transition(\n",
            "      (norm): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock2): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(240, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(240, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(336, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(336, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(432, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(432, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(528, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(528, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(576, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(624, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(624, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(720, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(720, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition2): _Transition(\n",
            "      (norm): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock3): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(432, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(432, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(528, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(528, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(576, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(624, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(624, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(720, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(720, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(816, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(816, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(864, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(912, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(912, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1008, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1008, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1056, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1104, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1200, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1248, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1296, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1296, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1344, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1392, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1392, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1440, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1488, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1488, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer25): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1536, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer26): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1584, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1584, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer27): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1632, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer28): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1680, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1680, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer29): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1728, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1728, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer30): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1776, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1776, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer31): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1824, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1824, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer32): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1872, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1872, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer33): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1920, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1920, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer34): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1968, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1968, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer35): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(2016, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(2016, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer36): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(2064, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(2064, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition3): _Transition(\n",
            "      (norm): BatchNorm2d(2112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(2112, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock4): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1056, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1104, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1200, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1248, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1296, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1296, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1344, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1392, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1392, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1440, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1488, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1488, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1536, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1584, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1584, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1632, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1680, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1680, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1728, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1728, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1776, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1776, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1824, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1824, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1872, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1872, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1920, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1920, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1968, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1968, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(2016, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(2016, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(2064, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(2064, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(2112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(2112, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(2160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(2160, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(192, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (norm5): BatchNorm2d(2208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (classifier): Linear(in_features=2208, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== densenet169 ===================================\n",
            "DenseNet(\n",
            "  (features): Sequential(\n",
            "    (conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "    (norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (relu0): ReLU(inplace=True)\n",
            "    (pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "    (denseblock1): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition1): _Transition(\n",
            "      (norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock2): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition2): _Transition(\n",
            "      (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock3): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer25): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1024, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer26): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1056, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer27): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1088, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1088, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer28): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1120, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer29): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1152, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer30): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1184, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1184, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer31): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1216, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1216, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer32): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1248, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition3): _Transition(\n",
            "      (norm): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock4): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1024, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1056, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1088, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1088, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1120, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1152, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1184, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1184, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1216, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1216, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1248, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1280, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1312, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1312, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1344, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1376, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1376, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer25): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1408, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1408, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer26): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1440, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer27): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1472, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1472, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer28): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1504, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1504, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer29): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1536, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer30): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1568, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1568, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer31): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1600, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer32): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1632, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (norm5): BatchNorm2d(1664, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (classifier): Linear(in_features=1664, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== densenet201 ===================================\n",
            "DenseNet(\n",
            "  (features): Sequential(\n",
            "    (conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "    (norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (relu0): ReLU(inplace=True)\n",
            "    (pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "    (denseblock1): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition1): _Transition(\n",
            "      (norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock2): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition2): _Transition(\n",
            "      (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock3): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer25): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1024, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer26): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1056, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer27): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1088, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1088, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer28): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1120, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer29): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1152, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer30): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1184, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1184, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer31): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1216, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1216, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer32): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1248, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer33): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1280, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer34): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1312, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1312, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer35): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1344, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer36): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1376, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1376, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer37): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1408, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1408, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer38): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1440, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer39): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1472, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1472, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer40): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1504, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1504, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer41): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1536, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer42): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1568, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1568, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer43): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1600, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer44): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1632, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer45): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1664, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1664, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer46): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1696, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1696, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer47): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1728, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1728, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer48): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1760, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1760, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (transition3): _Transition(\n",
            "      (norm): BatchNorm2d(1792, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv): Conv2d(1792, 896, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n",
            "    )\n",
            "    (denseblock4): _DenseBlock(\n",
            "      (denselayer1): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer2): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer3): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer4): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer5): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1024, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer6): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1056, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer7): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1088, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1088, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer8): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1120, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer9): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1152, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer10): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1184, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1184, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer11): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1216, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1216, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer12): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1248, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer13): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1280, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer14): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1312, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1312, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer15): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1344, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer16): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1376, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1376, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer17): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1408, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1408, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer18): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1440, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer19): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1472, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1472, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer20): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1504, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1504, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer21): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1536, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer22): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1568, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1568, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer23): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1600, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer24): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1632, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer25): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1664, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1664, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer26): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1696, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1696, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer27): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1728, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1728, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer28): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1760, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1760, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer29): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1792, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1792, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer30): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1824, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1824, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer31): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1856, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1856, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "      (denselayer32): _DenseLayer(\n",
            "        (norm1): BatchNorm2d(1888, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu1): ReLU(inplace=True)\n",
            "        (conv1): Conv2d(1888, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (relu2): ReLU(inplace=True)\n",
            "        (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      )\n",
            "    )\n",
            "    (norm5): BatchNorm2d(1920, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (classifier): Linear(in_features=1920, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== googlenet ===================================\n",
            "GoogLeNet(\n",
            "  (conv1): BasicConv2d(\n",
            "    (conv): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "    (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (maxpool1): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "  (conv2): BasicConv2d(\n",
            "    (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (conv3): BasicConv2d(\n",
            "    (conv): Conv2d(64, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "    (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (maxpool2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "  (inception3a): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(96, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(192, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(16, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(16, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (inception3b): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(32, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (maxpool3): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "  (inception4a): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(480, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(96, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(208, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(480, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(16, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(16, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(480, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (inception4b): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(512, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(112, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(112, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(224, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(24, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(24, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (inception4c): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(24, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(24, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (inception4d): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(112, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(512, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(144, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(144, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(288, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (inception4e): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(528, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(528, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(528, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(528, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (maxpool4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "  (inception5a): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(832, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(256, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(832, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(832, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (inception5b): Inception(\n",
            "    (branch1): BasicConv2d(\n",
            "      (conv): Conv2d(832, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch2): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(832, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch3): Sequential(\n",
            "      (0): BasicConv2d(\n",
            "        (conv): Conv2d(832, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(48, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (branch4): Sequential(\n",
            "      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=True)\n",
            "      (1): BasicConv2d(\n",
            "        (conv): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (aux1): None\n",
            "  (aux2): None\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (dropout): Dropout(p=0.2, inplace=False)\n",
            "  (fc): Linear(in_features=1024, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== inception_v3 ===================================\n",
            "Inception3(\n",
            "  (Conv2d_1a_3x3): BasicConv2d(\n",
            "    (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False)\n",
            "    (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (Conv2d_2a_3x3): BasicConv2d(\n",
            "    (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), bias=False)\n",
            "    (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (Conv2d_2b_3x3): BasicConv2d(\n",
            "    (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "    (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (maxpool1): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  (Conv2d_3b_1x1): BasicConv2d(\n",
            "    (conv): Conv2d(64, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (bn): BatchNorm2d(80, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (Conv2d_4a_3x3): BasicConv2d(\n",
            "    (conv): Conv2d(80, 192, kernel_size=(3, 3), stride=(1, 1), bias=False)\n",
            "    (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  )\n",
            "  (maxpool2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  (Mixed_5b): InceptionA(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch5x5_1): BasicConv2d(\n",
            "      (conv): Conv2d(192, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch5x5_2): BasicConv2d(\n",
            "      (conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_5c): InceptionA(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch5x5_1): BasicConv2d(\n",
            "      (conv): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch5x5_2): BasicConv2d(\n",
            "      (conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_5d): InceptionA(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch5x5_1): BasicConv2d(\n",
            "      (conv): Conv2d(288, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch5x5_2): BasicConv2d(\n",
            "      (conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_6a): InceptionB(\n",
            "    (branch3x3): BasicConv2d(\n",
            "      (conv): Conv2d(288, 384, kernel_size=(3, 3), stride=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_6b): InceptionC(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_2): BasicConv2d(\n",
            "      (conv): Conv2d(128, 128, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_3): BasicConv2d(\n",
            "      (conv): Conv2d(128, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(128, 128, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(128, 128, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_4): BasicConv2d(\n",
            "      (conv): Conv2d(128, 128, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_5): BasicConv2d(\n",
            "      (conv): Conv2d(128, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_6c): InceptionC(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_2): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_3): BasicConv2d(\n",
            "      (conv): Conv2d(160, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_4): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_5): BasicConv2d(\n",
            "      (conv): Conv2d(160, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_6d): InceptionC(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_2): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_3): BasicConv2d(\n",
            "      (conv): Conv2d(160, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_4): BasicConv2d(\n",
            "      (conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_5): BasicConv2d(\n",
            "      (conv): Conv2d(160, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_6e): InceptionC(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_2): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7_3): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_3): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_4): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7dbl_5): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (AuxLogits): InceptionAux(\n",
            "    (conv0): BasicConv2d(\n",
            "      (conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (conv1): BasicConv2d(\n",
            "      (conv): Conv2d(128, 768, kernel_size=(5, 5), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(768, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (fc): Linear(in_features=768, out_features=1000, bias=True)\n",
            "  )\n",
            "  (Mixed_7a): InceptionD(\n",
            "    (branch3x3_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_2): BasicConv2d(\n",
            "      (conv): Conv2d(192, 320, kernel_size=(3, 3), stride=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7x3_1): BasicConv2d(\n",
            "      (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7x3_2): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7x3_3): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch7x7x3_4): BasicConv2d(\n",
            "      (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_7b): InceptionE(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_1): BasicConv2d(\n",
            "      (conv): Conv2d(1280, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_2a): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_2b): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(1280, 448, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(448, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(448, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3a): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3b): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(1280, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (Mixed_7c): InceptionE(\n",
            "    (branch1x1): BasicConv2d(\n",
            "      (conv): Conv2d(2048, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_1): BasicConv2d(\n",
            "      (conv): Conv2d(2048, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_2a): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3_2b): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_1): BasicConv2d(\n",
            "      (conv): Conv2d(2048, 448, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(448, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_2): BasicConv2d(\n",
            "      (conv): Conv2d(448, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3a): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch3x3dbl_3b): BasicConv2d(\n",
            "      (conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)\n",
            "      (bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (branch_pool): BasicConv2d(\n",
            "      (conv): Conv2d(2048, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (dropout): Dropout(p=0.5, inplace=False)\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== mnasnet0_5 ===================================\n",
            "MNASNet(\n",
            "  (layers): Sequential(\n",
            "    (0): Conv2d(3, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "    (1): BatchNorm2d(16, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=16, bias=False)\n",
            "    (4): BatchNorm2d(16, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (5): ReLU(inplace=True)\n",
            "    (6): Conv2d(16, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (7): BatchNorm2d(8, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (8): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(8, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)\n",
            "          (4): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(24, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(16, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(16, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "          (4): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(48, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(16, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(16, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "          (4): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(48, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(16, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (9): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(16, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(48, 48, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=48, bias=False)\n",
            "          (4): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(48, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(24, 72, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(72, 72, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=72, bias=False)\n",
            "          (4): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(72, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(24, 72, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(72, 72, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=72, bias=False)\n",
            "          (4): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(72, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (10): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(144, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(144, 144, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=144, bias=False)\n",
            "          (4): BatchNorm2d(144, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(40, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=240, bias=False)\n",
            "          (4): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(40, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=240, bias=False)\n",
            "          (4): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(40, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (11): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(240, 240, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=240, bias=False)\n",
            "          (4): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(240, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(48, 288, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(288, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=288, bias=False)\n",
            "          (4): BatchNorm2d(288, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(288, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (12): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(48, 288, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(288, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(288, 288, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=288, bias=False)\n",
            "          (4): BatchNorm2d(288, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(288, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(96, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(576, 576, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=576, bias=False)\n",
            "          (4): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(96, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(576, 576, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=576, bias=False)\n",
            "          (4): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(96, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (3): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(576, 576, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=576, bias=False)\n",
            "          (4): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(96, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (13): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)\n",
            "          (4): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(160, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (14): Conv2d(160, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (15): BatchNorm2d(1280, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (16): ReLU(inplace=True)\n",
            "  )\n",
            "  (classifier): Sequential(\n",
            "    (0): Dropout(p=0.2, inplace=True)\n",
            "    (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== mnasnet1_0 ===================================\n",
            "MNASNet(\n",
            "  (layers): Sequential(\n",
            "    (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "    (1): BatchNorm2d(32, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "    (4): BatchNorm2d(32, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (5): ReLU(inplace=True)\n",
            "    (6): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (7): BatchNorm2d(16, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (8): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(16, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=48, bias=False)\n",
            "          (4): BatchNorm2d(48, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(48, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(24, 72, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(72, 72, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=72, bias=False)\n",
            "          (4): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(72, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(24, 72, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(72, 72, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=72, bias=False)\n",
            "          (4): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(72, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(24, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (9): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(24, 72, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(72, 72, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=72, bias=False)\n",
            "          (4): BatchNorm2d(72, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(72, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(40, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(40, 120, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(120, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(120, 120, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=120, bias=False)\n",
            "          (4): BatchNorm2d(120, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(120, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(40, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(40, 120, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(120, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(120, 120, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=120, bias=False)\n",
            "          (4): BatchNorm2d(120, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(120, 40, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(40, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (10): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(240, 240, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=240, bias=False)\n",
            "          (4): BatchNorm2d(240, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(240, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(80, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(480, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(480, 480, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=480, bias=False)\n",
            "          (4): BatchNorm2d(480, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(80, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(480, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(480, 480, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=480, bias=False)\n",
            "          (4): BatchNorm2d(480, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(480, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(80, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (11): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(80, 480, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(480, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(480, 480, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=480, bias=False)\n",
            "          (4): BatchNorm2d(480, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(480, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(96, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)\n",
            "          (4): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(96, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (12): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(576, 576, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=576, bias=False)\n",
            "          (4): BatchNorm2d(576, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(576, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(192, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (1): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)\n",
            "          (4): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(192, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (2): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)\n",
            "          (4): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(192, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "      (3): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(1152, 1152, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=1152, bias=False)\n",
            "          (4): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(1152, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(192, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (13): Sequential(\n",
            "      (0): _InvertedResidual(\n",
            "        (layers): Sequential(\n",
            "          (0): Conv2d(192, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (2): ReLU(inplace=True)\n",
            "          (3): Conv2d(1152, 1152, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1152, bias=False)\n",
            "          (4): BatchNorm2d(1152, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "          (5): ReLU(inplace=True)\n",
            "          (6): Conv2d(1152, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (7): BatchNorm2d(320, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "        )\n",
            "      )\n",
            "    )\n",
            "    (14): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (15): BatchNorm2d(1280, eps=1e-05, momentum=0.00029999999999996696, affine=True, track_running_stats=True)\n",
            "    (16): ReLU(inplace=True)\n",
            "  )\n",
            "  (classifier): Sequential(\n",
            "    (0): Dropout(p=0.2, inplace=True)\n",
            "    (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== mobilenet_v2 ===================================\n",
            "MobileNetV2(\n",
            "  (features): Sequential(\n",
            "    (0): ConvBNReLU(\n",
            "      (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (2): ReLU6(inplace=True)\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "          (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)\n",
            "          (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)\n",
            "          (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (4): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(144, 144, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=144, bias=False)\n",
            "          (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (5): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)\n",
            "          (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (6): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)\n",
            "          (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (7): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=192, bias=False)\n",
            "          (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (8): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (9): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (10): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (11): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)\n",
            "          (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (12): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (13): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (14): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=576, bias=False)\n",
            "          (1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (15): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)\n",
            "          (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (16): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)\n",
            "          (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (17): InvertedResidual(\n",
            "      (conv): Sequential(\n",
            "        (0): ConvBNReLU(\n",
            "          (0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "          (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (1): ConvBNReLU(\n",
            "          (0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)\n",
            "          (1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "          (2): ReLU6(inplace=True)\n",
            "        )\n",
            "        (2): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (18): ConvBNReLU(\n",
            "      (0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (2): ReLU6(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (classifier): Sequential(\n",
            "    (0): Dropout(p=0.2, inplace=False)\n",
            "    (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnet101 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (6): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (7): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (8): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (9): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (10): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (11): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (12): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (13): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (14): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (15): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (16): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (17): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (18): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (19): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (20): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (21): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (22): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnet152 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (6): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (7): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (6): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (7): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (8): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (9): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (10): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (11): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (12): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (13): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (14): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (15): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (16): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (17): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (18): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (19): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (20): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (21): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (22): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (23): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (24): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (25): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (26): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (27): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (28): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (29): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (30): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (31): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (32): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (33): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (34): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (35): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnet18 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=512, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnet34 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (2): BasicBlock(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (2): BasicBlock(\n",
            "      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (3): BasicBlock(\n",
            "      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (2): BasicBlock(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (3): BasicBlock(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (4): BasicBlock(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (5): BasicBlock(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): BasicBlock(\n",
            "      (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): BasicBlock(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "    (2): BasicBlock(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=512, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnet50 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnext101_32x8d ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (6): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (7): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (8): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (9): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (10): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (11): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (12): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (13): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (14): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (15): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (16): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (17): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (18): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (19): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (20): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (21): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (22): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(2048, 2048, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(2048, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== resnext50_32x4d ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== shufflenet_v2_x0_5 ===================================\n",
            "ShuffleNetV2(\n",
            "  (conv1): Sequential(\n",
            "    (0): Conv2d(3, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "    (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "  )\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (stage2): Sequential(\n",
            "    (0): InvertedResidual(\n",
            "      (branch1): Sequential(\n",
            "        (0): Conv2d(24, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)\n",
            "        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (4): ReLU(inplace=True)\n",
            "      )\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)\n",
            "        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)\n",
            "        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)\n",
            "        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)\n",
            "        (4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (stage3): Sequential(\n",
            "    (0): InvertedResidual(\n",
            "      (branch1): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=48, bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (4): ReLU(inplace=True)\n",
            "      )\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (4): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (5): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (6): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (7): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=48, bias=False)\n",
            "        (4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (stage4): Sequential(\n",
            "    (0): InvertedResidual(\n",
            "      (branch1): Sequential(\n",
            "        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)\n",
            "        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (4): ReLU(inplace=True)\n",
            "      )\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)\n",
            "        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)\n",
            "        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)\n",
            "        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=96, bias=False)\n",
            "        (4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (conv5): Sequential(\n",
            "    (0): Conv2d(192, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "  )\n",
            "  (fc): Linear(in_features=1024, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== shufflenet_v2_x1_0 ===================================\n",
            "ShuffleNetV2(\n",
            "  (conv1): Sequential(\n",
            "    (0): Conv2d(3, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "    (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "  )\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (stage2): Sequential(\n",
            "    (0): InvertedResidual(\n",
            "      (branch1): Sequential(\n",
            "        (0): Conv2d(24, 24, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)\n",
            "        (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): Conv2d(24, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (4): ReLU(inplace=True)\n",
            "      )\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(24, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(58, 58, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=58, bias=False)\n",
            "        (4): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(58, 58, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=58, bias=False)\n",
            "        (4): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(58, 58, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=58, bias=False)\n",
            "        (4): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(58, 58, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=58, bias=False)\n",
            "        (4): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(58, 58, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(58, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (stage3): Sequential(\n",
            "    (0): InvertedResidual(\n",
            "      (branch1): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=116, bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (4): ReLU(inplace=True)\n",
            "      )\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (4): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (5): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (6): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (7): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(116, 116, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=116, bias=False)\n",
            "        (4): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(116, 116, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(116, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (stage4): Sequential(\n",
            "    (0): InvertedResidual(\n",
            "      (branch1): Sequential(\n",
            "        (0): Conv2d(232, 232, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=232, bias=False)\n",
            "        (1): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (3): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (4): ReLU(inplace=True)\n",
            "      )\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(232, 232, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=232, bias=False)\n",
            "        (4): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (1): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(232, 232, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=232, bias=False)\n",
            "        (4): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (2): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(232, 232, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=232, bias=False)\n",
            "        (4): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "    (3): InvertedResidual(\n",
            "      (branch1): Sequential()\n",
            "      (branch2): Sequential(\n",
            "        (0): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (2): ReLU(inplace=True)\n",
            "        (3): Conv2d(232, 232, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=232, bias=False)\n",
            "        (4): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (5): Conv2d(232, 232, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (6): BatchNorm2d(232, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "        (7): ReLU(inplace=True)\n",
            "      )\n",
            "    )\n",
            "  )\n",
            "  (conv5): Sequential(\n",
            "    (0): Conv2d(464, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "    (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "  )\n",
            "  (fc): Linear(in_features=1024, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== squeezenet1_0 ===================================\n",
            "SqueezeNet(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 96, kernel_size=(7, 7), stride=(2, 2))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "    (3): Fire(\n",
            "      (squeeze): Conv2d(96, 16, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Fire(\n",
            "      (squeeze): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Fire(\n",
            "      (squeeze): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (6): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "    (7): Fire(\n",
            "      (squeeze): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (8): Fire(\n",
            "      (squeeze): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (9): Fire(\n",
            "      (squeeze): Conv2d(384, 48, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (10): Fire(\n",
            "      (squeeze): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (11): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "    (12): Fire(\n",
            "      (squeeze): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (classifier): Sequential(\n",
            "    (0): Dropout(p=0.5, inplace=False)\n",
            "    (1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== squeezenet1_1 ===================================\n",
            "SqueezeNet(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "    (3): Fire(\n",
            "      (squeeze): Conv2d(64, 16, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Fire(\n",
            "      (squeeze): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "    (6): Fire(\n",
            "      (squeeze): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (7): Fire(\n",
            "      (squeeze): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (8): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)\n",
            "    (9): Fire(\n",
            "      (squeeze): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (10): Fire(\n",
            "      (squeeze): Conv2d(384, 48, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (11): Fire(\n",
            "      (squeeze): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "    (12): Fire(\n",
            "      (squeeze): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (squeeze_activation): ReLU(inplace=True)\n",
            "      (expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))\n",
            "      (expand1x1_activation): ReLU(inplace=True)\n",
            "      (expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "      (expand3x3_activation): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (classifier): Sequential(\n",
            "    (0): Dropout(p=0.5, inplace=False)\n",
            "    (1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg11 ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (3): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (6): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (7): ReLU(inplace=True)\n",
            "    (8): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (9): ReLU(inplace=True)\n",
            "    (10): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (11): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (12): ReLU(inplace=True)\n",
            "    (13): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (14): ReLU(inplace=True)\n",
            "    (15): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (16): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (17): ReLU(inplace=True)\n",
            "    (18): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (19): ReLU(inplace=True)\n",
            "    (20): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg11_bn ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (4): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (5): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (6): ReLU(inplace=True)\n",
            "    (7): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (8): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (9): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (10): ReLU(inplace=True)\n",
            "    (11): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (12): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (13): ReLU(inplace=True)\n",
            "    (14): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (15): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (16): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (17): ReLU(inplace=True)\n",
            "    (18): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (19): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (20): ReLU(inplace=True)\n",
            "    (21): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (22): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (23): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (24): ReLU(inplace=True)\n",
            "    (25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (26): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (27): ReLU(inplace=True)\n",
            "    (28): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg13 ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (3): ReLU(inplace=True)\n",
            "    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (6): ReLU(inplace=True)\n",
            "    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (8): ReLU(inplace=True)\n",
            "    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): ReLU(inplace=True)\n",
            "    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (13): ReLU(inplace=True)\n",
            "    (14): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (15): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (16): ReLU(inplace=True)\n",
            "    (17): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (18): ReLU(inplace=True)\n",
            "    (19): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (20): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (21): ReLU(inplace=True)\n",
            "    (22): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (23): ReLU(inplace=True)\n",
            "    (24): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg13_bn ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (5): ReLU(inplace=True)\n",
            "    (6): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (7): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (9): ReLU(inplace=True)\n",
            "    (10): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (12): ReLU(inplace=True)\n",
            "    (13): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (14): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (15): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (16): ReLU(inplace=True)\n",
            "    (17): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (18): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (19): ReLU(inplace=True)\n",
            "    (20): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (21): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (22): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (23): ReLU(inplace=True)\n",
            "    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (25): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (26): ReLU(inplace=True)\n",
            "    (27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (29): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (30): ReLU(inplace=True)\n",
            "    (31): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (32): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (33): ReLU(inplace=True)\n",
            "    (34): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg16 ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (3): ReLU(inplace=True)\n",
            "    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (6): ReLU(inplace=True)\n",
            "    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (8): ReLU(inplace=True)\n",
            "    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): ReLU(inplace=True)\n",
            "    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (13): ReLU(inplace=True)\n",
            "    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (15): ReLU(inplace=True)\n",
            "    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (18): ReLU(inplace=True)\n",
            "    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (20): ReLU(inplace=True)\n",
            "    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (22): ReLU(inplace=True)\n",
            "    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (25): ReLU(inplace=True)\n",
            "    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (27): ReLU(inplace=True)\n",
            "    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (29): ReLU(inplace=True)\n",
            "    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg16_bn ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (5): ReLU(inplace=True)\n",
            "    (6): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (7): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (9): ReLU(inplace=True)\n",
            "    (10): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (12): ReLU(inplace=True)\n",
            "    (13): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (14): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (15): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (16): ReLU(inplace=True)\n",
            "    (17): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (18): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (19): ReLU(inplace=True)\n",
            "    (20): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (21): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (22): ReLU(inplace=True)\n",
            "    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (24): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (25): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (26): ReLU(inplace=True)\n",
            "    (27): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (28): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (29): ReLU(inplace=True)\n",
            "    (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (31): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (32): ReLU(inplace=True)\n",
            "    (33): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (35): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (36): ReLU(inplace=True)\n",
            "    (37): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (38): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (39): ReLU(inplace=True)\n",
            "    (40): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (41): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (42): ReLU(inplace=True)\n",
            "    (43): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg19 ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (3): ReLU(inplace=True)\n",
            "    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (6): ReLU(inplace=True)\n",
            "    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (8): ReLU(inplace=True)\n",
            "    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): ReLU(inplace=True)\n",
            "    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (13): ReLU(inplace=True)\n",
            "    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (15): ReLU(inplace=True)\n",
            "    (16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (17): ReLU(inplace=True)\n",
            "    (18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (20): ReLU(inplace=True)\n",
            "    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (22): ReLU(inplace=True)\n",
            "    (23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (24): ReLU(inplace=True)\n",
            "    (25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (26): ReLU(inplace=True)\n",
            "    (27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (29): ReLU(inplace=True)\n",
            "    (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (31): ReLU(inplace=True)\n",
            "    (32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (33): ReLU(inplace=True)\n",
            "    (34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (35): ReLU(inplace=True)\n",
            "    (36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== vgg19_bn ===================================\n",
            "VGG(\n",
            "  (features): Sequential(\n",
            "    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (2): ReLU(inplace=True)\n",
            "    (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (5): ReLU(inplace=True)\n",
            "    (6): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (7): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (9): ReLU(inplace=True)\n",
            "    (10): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (11): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (12): ReLU(inplace=True)\n",
            "    (13): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (14): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (15): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (16): ReLU(inplace=True)\n",
            "    (17): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (18): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (19): ReLU(inplace=True)\n",
            "    (20): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (21): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (22): ReLU(inplace=True)\n",
            "    (23): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (24): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (25): ReLU(inplace=True)\n",
            "    (26): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (27): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (28): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (29): ReLU(inplace=True)\n",
            "    (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (31): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (32): ReLU(inplace=True)\n",
            "    (33): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (34): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (35): ReLU(inplace=True)\n",
            "    (36): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (37): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (38): ReLU(inplace=True)\n",
            "    (39): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "    (40): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (41): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (42): ReLU(inplace=True)\n",
            "    (43): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (44): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (45): ReLU(inplace=True)\n",
            "    (46): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (47): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (48): ReLU(inplace=True)\n",
            "    (49): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
            "    (50): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "    (51): ReLU(inplace=True)\n",
            "    (52): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))\n",
            "  (classifier): Sequential(\n",
            "    (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "    (1): ReLU(inplace=True)\n",
            "    (2): Dropout(p=0.5, inplace=False)\n",
            "    (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "    (4): ReLU(inplace=True)\n",
            "    (5): Dropout(p=0.5, inplace=False)\n",
            "    (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            "  )\n",
            ") \n",
            "\n",
            "\n",
            "=================================== wide_resnet101_2 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (6): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (7): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (8): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (9): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (10): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (11): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (12): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (13): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (14): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (15): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (16): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (17): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (18): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (19): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (20): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (21): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (22): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n",
            "=================================== wide_resnet50_2 ===================================\n",
            "ResNet(\n",
            "  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n",
            "  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "  (relu): ReLU(inplace=True)\n",
            "  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n",
            "  (layer1): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer2): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer3): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (3): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (4): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (5): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (layer4): Sequential(\n",
            "    (0): Bottleneck(\n",
            "      (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "      (downsample): Sequential(\n",
            "        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n",
            "        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      )\n",
            "    )\n",
            "    (1): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "    (2): Bottleneck(\n",
            "      (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n",
            "      (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n",
            "      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
            "      (relu): ReLU(inplace=True)\n",
            "    )\n",
            "  )\n",
            "  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            "  (fc): Linear(in_features=2048, out_features=1000, bias=True)\n",
            ") \n",
            "\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "roAu-dHb-0kO",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 357
        },
        "outputId": "9cca1ad4-a31e-49c2-bd65-b8e22ed80034"
      },
      "source": [
        "dont_have_classifier = []\n",
        "have_classifier = []\n",
        "\n",
        "print(\"Models containing classifier attribute\\n\")\n",
        "for model_name, model in model_list:\n",
        "    try:\n",
        "        if getattr(model, \"classifier\"):\n",
        "            print(model_name)\n",
        "            have_classifier.append((model_name, model))\n",
        "    except:\n",
        "        dont_have_classifier.append((model_name, model))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Models containing classifier attribute\n",
            "\n",
            "alexnet\n",
            "densenet121\n",
            "densenet161\n",
            "densenet169\n",
            "densenet201\n",
            "mnasnet0_5\n",
            "mnasnet1_0\n",
            "mobilenet_v2\n",
            "squeezenet1_0\n",
            "squeezenet1_1\n",
            "vgg11\n",
            "vgg11_bn\n",
            "vgg13\n",
            "vgg13_bn\n",
            "vgg16\n",
            "vgg16_bn\n",
            "vgg19\n",
            "vgg19_bn\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4EcQOGL4ClvQ",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 272
        },
        "outputId": "4081a500-b1b3-4cb4-d1da-5d71246830f4"
      },
      "source": [
        "print(\"Models not containing classifier attribute\\n\")\n",
        "print(*list(list(zip(*dont_have_classifier))[0]), sep=\"\\n\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Models not containing classifier attribute\n",
            "\n",
            "googlenet\n",
            "inception_v3\n",
            "resnet101\n",
            "resnet152\n",
            "resnet18\n",
            "resnet34\n",
            "resnet50\n",
            "resnext101_32x8d\n",
            "resnext50_32x4d\n",
            "shufflenet_v2_x0_5\n",
            "shufflenet_v2_x1_0\n",
            "wide_resnet101_2\n",
            "wide_resnet50_2\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "H7-ujbjxElJA",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "e7d44abe-2f6b-4c6d-9c4c-1004646ebbdb"
      },
      "source": [
        "for model_name, model in have_classifier:\n",
        "    print(model_name)\n",
        "    print(model.classifier)\n",
        "    print()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "alexnet\n",
            "Sequential(\n",
            "  (0): Dropout(p=0.5, inplace=False)\n",
            "  (1): Linear(in_features=9216, out_features=4096, bias=True)\n",
            "  (2): ReLU(inplace=True)\n",
            "  (3): Dropout(p=0.5, inplace=False)\n",
            "  (4): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (5): ReLU(inplace=True)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "densenet121\n",
            "Linear(in_features=1024, out_features=1000, bias=True)\n",
            "\n",
            "densenet161\n",
            "Linear(in_features=2208, out_features=1000, bias=True)\n",
            "\n",
            "densenet169\n",
            "Linear(in_features=1664, out_features=1000, bias=True)\n",
            "\n",
            "densenet201\n",
            "Linear(in_features=1920, out_features=1000, bias=True)\n",
            "\n",
            "mnasnet0_5\n",
            "Sequential(\n",
            "  (0): Dropout(p=0.2, inplace=True)\n",
            "  (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "mnasnet1_0\n",
            "Sequential(\n",
            "  (0): Dropout(p=0.2, inplace=True)\n",
            "  (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "mobilenet_v2\n",
            "Sequential(\n",
            "  (0): Dropout(p=0.2, inplace=False)\n",
            "  (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "squeezenet1_0\n",
            "Sequential(\n",
            "  (0): Dropout(p=0.5, inplace=False)\n",
            "  (1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))\n",
            "  (2): ReLU(inplace=True)\n",
            "  (3): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            ")\n",
            "\n",
            "squeezenet1_1\n",
            "Sequential(\n",
            "  (0): Dropout(p=0.5, inplace=False)\n",
            "  (1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))\n",
            "  (2): ReLU(inplace=True)\n",
            "  (3): AdaptiveAvgPool2d(output_size=(1, 1))\n",
            ")\n",
            "\n",
            "vgg11\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg11_bn\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg13\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg13_bn\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg16\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg16_bn\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg19\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n",
            "vgg19_bn\n",
            "Sequential(\n",
            "  (0): Linear(in_features=25088, out_features=4096, bias=True)\n",
            "  (1): ReLU(inplace=True)\n",
            "  (2): Dropout(p=0.5, inplace=False)\n",
            "  (3): Linear(in_features=4096, out_features=4096, bias=True)\n",
            "  (4): ReLU(inplace=True)\n",
            "  (5): Dropout(p=0.5, inplace=False)\n",
            "  (6): Linear(in_features=4096, out_features=1000, bias=True)\n",
            ")\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RbGD53ZLE5X2",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 680
        },
        "outputId": "ead3eb42-af32-48d5-95d1-48eb5b332553"
      },
      "source": [
        "for model_name, model in dont_have_classifier:\n",
        "    print(model_name)\n",
        "    print(model.fc)\n",
        "    print()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "googlenet\n",
            "Linear(in_features=1024, out_features=1000, bias=True)\n",
            "\n",
            "inception_v3\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "resnet101\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "resnet152\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "resnet18\n",
            "Linear(in_features=512, out_features=1000, bias=True)\n",
            "\n",
            "resnet34\n",
            "Linear(in_features=512, out_features=1000, bias=True)\n",
            "\n",
            "resnet50\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "resnext101_32x8d\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "resnext50_32x4d\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "shufflenet_v2_x0_5\n",
            "Linear(in_features=1024, out_features=1000, bias=True)\n",
            "\n",
            "shufflenet_v2_x1_0\n",
            "Linear(in_features=1024, out_features=1000, bias=True)\n",
            "\n",
            "wide_resnet101_2\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n",
            "wide_resnet50_2\n",
            "Linear(in_features=2048, out_features=1000, bias=True)\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ily52WFWGK_A",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "b823c57e-95d7-4254-cfb5-f2ff9edb9d75"
      },
      "source": [
        "from torchsummary import summary\n",
        "\n",
        "for model_name, model in model_list:\n",
        "    try:\n",
        "        print(\"============================ \" + model_name + \" ============================\")\n",
        "        print(summary(model, (3, 224, 224), 32), \"\\n\\n\")\n",
        "    except:\n",
        "        print(\"torchsummary doesn't support DenseLayer. See: https://github.com/sksq96/pytorch-summary/pull/116 \\n\\n\")\n",
        "        pass"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "============================ alexnet ============================\n",
            "----------------------------------------------------------------\n",
            "        Layer (type)               Output Shape         Param #\n",
            "================================================================\n",
            "            Conv2d-1           [32, 64, 55, 55]          23,296\n",
            "              ReLU-2           [32, 64, 55, 55]               0\n",
            "         MaxPool2d-3           [32, 64, 27, 27]               0\n",
            "            Conv2d-4          [32, 192, 27, 27]         307,392\n",
            "              ReLU-5          [32, 192, 27, 27]               0\n",
            "         MaxPool2d-6          [32, 192, 13, 13]               0\n",
            "            Conv2d-7          [32, 384, 13, 13]         663,936\n",
            "              ReLU-8          [32, 384, 13, 13]               0\n",
            "            Conv2d-9          [32, 256, 13, 13]         884,992\n",
            "             ReLU-10          [32, 256, 13, 13]               0\n",
            "           Conv2d-11          [32, 256, 13, 13]         590,080\n",
            "             ReLU-12          [32, 256, 13, 13]               0\n",
            "        MaxPool2d-13            [32, 256, 6, 6]               0\n",
            "AdaptiveAvgPool2d-14            [32, 256, 6, 6]               0\n",
            "          Dropout-15                 [32, 9216]               0\n",
            "           Linear-16                 [32, 4096]      37,752,832\n",
            "             ReLU-17                 [32, 4096]               0\n",
            "          Dropout-18                 [32, 4096]               0\n",
            "           Linear-19                 [32, 4096]      16,781,312\n",
            "             ReLU-20                 [32, 4096]               0\n",
            "           Linear-21                 [32, 1000]       4,097,000\n",
            "================================================================\n",
            "Total params: 61,100,840\n",
            "Trainable params: 61,100,840\n",
            "Non-trainable params: 0\n",
            "----------------------------------------------------------------\n",
            "Input size (MB): 18.38\n",
            "Forward/backward pass size (MB): 268.12\n",
            "Params size (MB): 233.08\n",
            "Estimated Total Size (MB): 519.58\n",
            "----------------------------------------------------------------\n",
            "None \n",
            "\n",
            "\n",
            "============================ densenet121 ============================\n",
            "torchsummary doesn't support DenseLayer. See: https://github.com/sksq96/pytorch-summary/pull/116 \n",
            "\n",
            "\n",
            "============================ densenet161 ============================\n",
            "torchsummary doesn't support DenseLayer. See: https://github.com/sksq96/pytorch-summary/pull/116 \n",
            "\n",
            "\n",
            "============================ densenet169 ============================\n",
            "torchsummary doesn't support DenseLayer. See: https://github.com/sksq96/pytorch-summary/pull/116 \n",
            "\n",
            "\n",
            "============================ densenet201 ============================\n",
            "torchsummary doesn't support DenseLayer. See: https://github.com/sksq96/pytorch-summary/pull/116 \n",
            "\n",
            "\n",
            "============================ googlenet ============================\n",
            "----------------------------------------------------------------\n",
            "        Layer (type)               Output Shape         Param #\n",
            "================================================================\n",
            "            Conv2d-1         [32, 64, 112, 112]           9,408\n",
            "       BatchNorm2d-2         [32, 64, 112, 112]             128\n",
            "       BasicConv2d-3         [32, 64, 112, 112]               0\n",
            "         MaxPool2d-4           [32, 64, 56, 56]               0\n",
            "            Conv2d-5           [32, 64, 56, 56]           4,096\n",
            "       BatchNorm2d-6           [32, 64, 56, 56]             128\n",
            "       BasicConv2d-7           [32, 64, 56, 56]               0\n",
            "            Conv2d-8          [32, 192, 56, 56]         110,592\n",
            "       BatchNorm2d-9          [32, 192, 56, 56]             384\n",
            "      BasicConv2d-10          [32, 192, 56, 56]               0\n",
            "        MaxPool2d-11          [32, 192, 28, 28]               0\n",
            "           Conv2d-12           [32, 64, 28, 28]          12,288\n",
            "      BatchNorm2d-13           [32, 64, 28, 28]             128\n",
            "      BasicConv2d-14           [32, 64, 28, 28]               0\n",
            "           Conv2d-15           [32, 96, 28, 28]          18,432\n",
            "      BatchNorm2d-16           [32, 96, 28, 28]             192\n",
            "      BasicConv2d-17           [32, 96, 28, 28]               0\n",
            "           Conv2d-18          [32, 128, 28, 28]         110,592\n",
            "      BatchNorm2d-19          [32, 128, 28, 28]             256\n",
            "      BasicConv2d-20          [32, 128, 28, 28]               0\n",
            "           Conv2d-21           [32, 16, 28, 28]           3,072\n",
            "      BatchNorm2d-22           [32, 16, 28, 28]              32\n",
            "      BasicConv2d-23           [32, 16, 28, 28]               0\n",
            "           Conv2d-24           [32, 32, 28, 28]           4,608\n",
            "      BatchNorm2d-25           [32, 32, 28, 28]              64\n",
            "      BasicConv2d-26           [32, 32, 28, 28]               0\n",
            "        MaxPool2d-27          [32, 192, 28, 28]               0\n",
            "           Conv2d-28           [32, 32, 28, 28]           6,144\n",
            "      BatchNorm2d-29           [32, 32, 28, 28]              64\n",
            "      BasicConv2d-30           [32, 32, 28, 28]               0\n",
            "        Inception-31          [32, 256, 28, 28]               0\n",
            "           Conv2d-32          [32, 128, 28, 28]          32,768\n",
            "      BatchNorm2d-33          [32, 128, 28, 28]             256\n",
            "      BasicConv2d-34          [32, 128, 28, 28]               0\n",
            "           Conv2d-35          [32, 128, 28, 28]          32,768\n",
            "      BatchNorm2d-36          [32, 128, 28, 28]             256\n",
            "      BasicConv2d-37          [32, 128, 28, 28]               0\n",
            "           Conv2d-38          [32, 192, 28, 28]         221,184\n",
            "      BatchNorm2d-39          [32, 192, 28, 28]             384\n",
            "      BasicConv2d-40          [32, 192, 28, 28]               0\n",
            "           Conv2d-41           [32, 32, 28, 28]           8,192\n",
            "      BatchNorm2d-42           [32, 32, 28, 28]              64\n",
            "      BasicConv2d-43           [32, 32, 28, 28]               0\n",
            "           Conv2d-44           [32, 96, 28, 28]          27,648\n",
            "      BatchNorm2d-45           [32, 96, 28, 28]             192\n",
            "      BasicConv2d-46           [32, 96, 28, 28]               0\n",
            "        MaxPool2d-47          [32, 256, 28, 28]               0\n",
            "           Conv2d-48           [32, 64, 28, 28]          16,384\n",
            "      BatchNorm2d-49           [32, 64, 28, 28]             128\n",
            "      BasicConv2d-50           [32, 64, 28, 28]               0\n",
            "        Inception-51          [32, 480, 28, 28]               0\n",
            "        MaxPool2d-52          [32, 480, 14, 14]               0\n",
            "           Conv2d-53          [32, 192, 14, 14]          92,160\n",
            "      BatchNorm2d-54          [32, 192, 14, 14]             384\n",
            "      BasicConv2d-55          [32, 192, 14, 14]               0\n",
            "           Conv2d-56           [32, 96, 14, 14]          46,080\n",
            "      BatchNorm2d-57           [32, 96, 14, 14]             192\n",
            "      BasicConv2d-58           [32, 96, 14, 14]               0\n",
            "           Conv2d-59          [32, 208, 14, 14]         179,712\n",
            "      BatchNorm2d-60          [32, 208, 14, 14]             416\n",
            "      BasicConv2d-61          [32, 208, 14, 14]               0\n",
            "           Conv2d-62           [32, 16, 14, 14]           7,680\n",
            "      BatchNorm2d-63           [32, 16, 14, 14]              32\n",
            "      BasicConv2d-64           [32, 16, 14, 14]               0\n",
            "           Conv2d-65           [32, 48, 14, 14]           6,912\n",
            "      BatchNorm2d-66           [32, 48, 14, 14]              96\n",
            "      BasicConv2d-67           [32, 48, 14, 14]               0\n",
            "        MaxPool2d-68          [32, 480, 14, 14]               0\n",
            "           Conv2d-69           [32, 64, 14, 14]          30,720\n",
            "      BatchNorm2d-70           [32, 64, 14, 14]             128\n",
            "      BasicConv2d-71           [32, 64, 14, 14]               0\n",
            "        Inception-72          [32, 512, 14, 14]               0\n",
            "           Conv2d-73          [32, 160, 14, 14]          81,920\n",
            "      BatchNorm2d-74          [32, 160, 14, 14]             320\n",
            "      BasicConv2d-75          [32, 160, 14, 14]               0\n",
            "           Conv2d-76          [32, 112, 14, 14]          57,344\n",
            "      BatchNorm2d-77          [32, 112, 14, 14]             224\n",
            "      BasicConv2d-78          [32, 112, 14, 14]               0\n",
            "           Conv2d-79          [32, 224, 14, 14]         225,792\n",
            "      BatchNorm2d-80          [32, 224, 14, 14]             448\n",
            "      BasicConv2d-81          [32, 224, 14, 14]               0\n",
            "           Conv2d-82           [32, 24, 14, 14]          12,288\n",
            "      BatchNorm2d-83           [32, 24, 14, 14]              48\n",
            "      BasicConv2d-84           [32, 24, 14, 14]               0\n",
            "           Conv2d-85           [32, 64, 14, 14]          13,824\n",
            "      BatchNorm2d-86           [32, 64, 14, 14]             128\n",
            "      BasicConv2d-87           [32, 64, 14, 14]               0\n",
            "        MaxPool2d-88          [32, 512, 14, 14]               0\n",
            "           Conv2d-89           [32, 64, 14, 14]          32,768\n",
            "      BatchNorm2d-90           [32, 64, 14, 14]             128\n",
            "      BasicConv2d-91           [32, 64, 14, 14]               0\n",
            "        Inception-92          [32, 512, 14, 14]               0\n",
            "           Conv2d-93          [32, 128, 14, 14]          65,536\n",
            "      BatchNorm2d-94          [32, 128, 14, 14]             256\n",
            "      BasicConv2d-95          [32, 128, 14, 14]               0\n",
            "           Conv2d-96          [32, 128, 14, 14]          65,536\n",
            "      BatchNorm2d-97          [32, 128, 14, 14]             256\n",
            "      BasicConv2d-98          [32, 128, 14, 14]               0\n",
            "           Conv2d-99          [32, 256, 14, 14]         294,912\n",
            "     BatchNorm2d-100          [32, 256, 14, 14]             512\n",
            "     BasicConv2d-101          [32, 256, 14, 14]               0\n",
            "          Conv2d-102           [32, 24, 14, 14]          12,288\n",
            "     BatchNorm2d-103           [32, 24, 14, 14]              48\n",
            "     BasicConv2d-104           [32, 24, 14, 14]               0\n",
            "          Conv2d-105           [32, 64, 14, 14]          13,824\n",
            "     BatchNorm2d-106           [32, 64, 14, 14]             128\n",
            "     BasicConv2d-107           [32, 64, 14, 14]               0\n",
            "       MaxPool2d-108          [32, 512, 14, 14]               0\n",
            "          Conv2d-109           [32, 64, 14, 14]          32,768\n",
            "     BatchNorm2d-110           [32, 64, 14, 14]             128\n",
            "     BasicConv2d-111           [32, 64, 14, 14]               0\n",
            "       Inception-112          [32, 512, 14, 14]               0\n",
            "          Conv2d-113          [32, 112, 14, 14]          57,344\n",
            "     BatchNorm2d-114          [32, 112, 14, 14]             224\n",
            "     BasicConv2d-115          [32, 112, 14, 14]               0\n",
            "          Conv2d-116          [32, 144, 14, 14]          73,728\n",
            "     BatchNorm2d-117          [32, 144, 14, 14]             288\n",
            "     BasicConv2d-118          [32, 144, 14, 14]               0\n",
            "          Conv2d-119          [32, 288, 14, 14]         373,248\n",
            "     BatchNorm2d-120          [32, 288, 14, 14]             576\n",
            "     BasicConv2d-121          [32, 288, 14, 14]               0\n",
            "          Conv2d-122           [32, 32, 14, 14]          16,384\n",
            "     BatchNorm2d-123           [32, 32, 14, 14]              64\n",
            "     BasicConv2d-124           [32, 32, 14, 14]               0\n",
            "          Conv2d-125           [32, 64, 14, 14]          18,432\n",
            "     BatchNorm2d-126           [32, 64, 14, 14]             128\n",
            "     BasicConv2d-127           [32, 64, 14, 14]               0\n",
            "       MaxPool2d-128          [32, 512, 14, 14]               0\n",
            "          Conv2d-129           [32, 64, 14, 14]          32,768\n",
            "     BatchNorm2d-130           [32, 64, 14, 14]             128\n",
            "     BasicConv2d-131           [32, 64, 14, 14]               0\n",
            "       Inception-132          [32, 528, 14, 14]               0\n",
            "          Conv2d-133          [32, 256, 14, 14]         135,168\n",
            "     BatchNorm2d-134          [32, 256, 14, 14]             512\n",
            "     BasicConv2d-135          [32, 256, 14, 14]               0\n",
            "          Conv2d-136          [32, 160, 14, 14]          84,480\n",
            "     BatchNorm2d-137          [32, 160, 14, 14]             320\n",
            "     BasicConv2d-138          [32, 160, 14, 14]               0\n",
            "          Conv2d-139          [32, 320, 14, 14]         460,800\n",
            "     BatchNorm2d-140          [32, 320, 14, 14]             640\n",
            "     BasicConv2d-141          [32, 320, 14, 14]               0\n",
            "          Conv2d-142           [32, 32, 14, 14]          16,896\n",
            "     BatchNorm2d-143           [32, 32, 14, 14]              64\n",
            "     BasicConv2d-144           [32, 32, 14, 14]               0\n",
            "          Conv2d-145          [32, 128, 14, 14]          36,864\n",
            "     BatchNorm2d-146          [32, 128, 14, 14]             256\n",
            "     BasicConv2d-147          [32, 128, 14, 14]               0\n",
            "       MaxPool2d-148          [32, 528, 14, 14]               0\n",
            "          Conv2d-149          [32, 128, 14, 14]          67,584\n",
            "     BatchNorm2d-150          [32, 128, 14, 14]             256\n",
            "     BasicConv2d-151          [32, 128, 14, 14]               0\n",
            "       Inception-152          [32, 832, 14, 14]               0\n",
            "       MaxPool2d-153            [32, 832, 7, 7]               0\n",
            "          Conv2d-154            [32, 256, 7, 7]         212,992\n",
            "     BatchNorm2d-155            [32, 256, 7, 7]             512\n",
            "     BasicConv2d-156            [32, 256, 7, 7]               0\n",
            "          Conv2d-157            [32, 160, 7, 7]         133,120\n",
            "     BatchNorm2d-158            [32, 160, 7, 7]             320\n",
            "     BasicConv2d-159            [32, 160, 7, 7]               0\n",
            "          Conv2d-160            [32, 320, 7, 7]         460,800\n",
            "     BatchNorm2d-161            [32, 320, 7, 7]             640\n",
            "     BasicConv2d-162            [32, 320, 7, 7]               0\n",
            "          Conv2d-163             [32, 32, 7, 7]          26,624\n",
            "     BatchNorm2d-164             [32, 32, 7, 7]              64\n",
            "     BasicConv2d-165             [32, 32, 7, 7]               0\n",
            "          Conv2d-166            [32, 128, 7, 7]          36,864\n",
            "     BatchNorm2d-167            [32, 128, 7, 7]             256\n",
            "     BasicConv2d-168            [32, 128, 7, 7]               0\n",
            "       MaxPool2d-169            [32, 832, 7, 7]               0\n",
            "          Conv2d-170            [32, 128, 7, 7]         106,496\n",
            "     BatchNorm2d-171            [32, 128, 7, 7]             256\n",
            "     BasicConv2d-172            [32, 128, 7, 7]               0\n",
            "       Inception-173            [32, 832, 7, 7]               0\n",
            "          Conv2d-174            [32, 384, 7, 7]         319,488\n",
            "     BatchNorm2d-175            [32, 384, 7, 7]             768\n",
            "     BasicConv2d-176            [32, 384, 7, 7]               0\n",
            "          Conv2d-177            [32, 192, 7, 7]         159,744\n",
            "     BatchNorm2d-178            [32, 192, 7, 7]             384\n",
            "     BasicConv2d-179            [32, 192, 7, 7]               0\n",
            "          Conv2d-180            [32, 384, 7, 7]         663,552\n",
            "     BatchNorm2d-181            [32, 384, 7, 7]             768\n",
            "     BasicConv2d-182            [32, 384, 7, 7]               0\n",
            "          Conv2d-183             [32, 48, 7, 7]          39,936\n",
            "     BatchNorm2d-184             [32, 48, 7, 7]              96\n",
            "     BasicConv2d-185             [32, 48, 7, 7]               0\n",
            "          Conv2d-186            [32, 128, 7, 7]          55,296\n",
            "     BatchNorm2d-187            [32, 128, 7, 7]             256\n",
            "     BasicConv2d-188            [32, 128, 7, 7]               0\n",
            "       MaxPool2d-189            [32, 832, 7, 7]               0\n",
            "          Conv2d-190            [32, 128, 7, 7]         106,496\n",
            "     BatchNorm2d-191            [32, 128, 7, 7]             256\n",
            "     BasicConv2d-192            [32, 128, 7, 7]               0\n",
            "       Inception-193           [32, 1024, 7, 7]               0\n",
            "AdaptiveAvgPool2d-194           [32, 1024, 1, 1]               0\n",
            "         Dropout-195                 [32, 1024]               0\n",
            "          Linear-196                 [32, 1000]       1,025,000\n",
            "================================================================\n",
            "Total params: 6,624,904\n",
            "Trainable params: 6,624,904\n",
            "Non-trainable params: 0\n",
            "----------------------------------------------------------------\n",
            "Input size (MB): 18.38\n",
            "Forward/backward pass size (MB): 3011.37\n",
            "Params size (MB): 25.27\n",
            "Estimated Total Size (MB): 3055.02\n",
            "----------------------------------------------------------------\n",
            "None \n",
            "\n",
            "\n",
            "============================ inception_v3 ============================\n",
            "torchsummary doesn't support DenseLayer. See: https://github.com/sksq96/pytorch-summary/pull/116 \n",
            "\n",
            "\n",
            "============================ mnasnet0_5 ============================\n",
            "----------------------------------------------------------------\n",
            "        Layer (type)               Output Shape         Param #\n",
            "================================================================\n",
            "            Conv2d-1         [32, 16, 112, 112]             432\n",
            "       BatchNorm2d-2         [32, 16, 112, 112]              32\n",
            "              ReLU-3         [32, 16, 112, 112]               0\n",
            "            Conv2d-4         [32, 16, 112, 112]             144\n",
            "       BatchNorm2d-5         [32, 16, 112, 112]              32\n",
            "              ReLU-6         [32, 16, 112, 112]               0\n",
            "            Conv2d-7          [32, 8, 112, 112]             128\n",
            "       BatchNorm2d-8          [32, 8, 112, 112]              16\n",
            "            Conv2d-9         [32, 24, 112, 112]             192\n",
            "      BatchNorm2d-10         [32, 24, 112, 112]              48\n",
            "             ReLU-11         [32, 24, 112, 112]               0\n",
            "           Conv2d-12           [32, 24, 56, 56]             216\n",
            "      BatchNorm2d-13           [32, 24, 56, 56]              48\n",
            "             ReLU-14           [32, 24, 56, 56]               0\n",
            "           Conv2d-15           [32, 16, 56, 56]             384\n",
            "      BatchNorm2d-16           [32, 16, 56, 56]              32\n",
            "_InvertedResidual-17           [32, 16, 56, 56]               0\n",
            "           Conv2d-18           [32, 48, 56, 56]             768\n",
            "      BatchNorm2d-19           [32, 48, 56, 56]              96\n",
            "             ReLU-20           [32, 48, 56, 56]               0\n",
            "           Conv2d-21           [32, 48, 56, 56]             432\n",
            "      BatchNorm2d-22           [32, 48, 56, 56]              96\n",
            "             ReLU-23           [32, 48, 56, 56]               0\n",
            "           Conv2d-24           [32, 16, 56, 56]             768\n",
            "      BatchNorm2d-25           [32, 16, 56, 56]              32\n",
            "_InvertedResidual-26           [32, 16, 56, 56]               0\n",
            "           Conv2d-27           [32, 48, 56, 56]             768\n",
            "      BatchNorm2d-28           [32, 48, 56, 56]              96\n",
            "             ReLU-29           [32, 48, 56, 56]               0\n",
            "           Conv2d-30           [32, 48, 56, 56]             432\n",
            "      BatchNorm2d-31           [32, 48, 56, 56]              96\n",
            "             ReLU-32           [32, 48, 56, 56]               0\n",
            "           Conv2d-33           [32, 16, 56, 56]             768\n",
            "      BatchNorm2d-34           [32, 16, 56, 56]              32\n",
            "_InvertedResidual-35           [32, 16, 56, 56]               0\n",
            "           Conv2d-36           [32, 48, 56, 56]             768\n",
            "      BatchNorm2d-37           [32, 48, 56, 56]              96\n",
            "             ReLU-38           [32, 48, 56, 56]               0\n",
            "           Conv2d-39           [32, 48, 28, 28]           1,200\n",
            "      BatchNorm2d-40           [32, 48, 28, 28]              96\n",
            "             ReLU-41           [32, 48, 28, 28]               0\n",
            "           Conv2d-42           [32, 24, 28, 28]           1,152\n",
            "      BatchNorm2d-43           [32, 24, 28, 28]              48\n",
            "_InvertedResidual-44           [32, 24, 28, 28]               0\n",
            "           Conv2d-45           [32, 72, 28, 28]           1,728\n",
            "      BatchNorm2d-46           [32, 72, 28, 28]             144\n",
            "             ReLU-47           [32, 72, 28, 28]               0\n",
            "           Conv2d-48           [32, 72, 28, 28]           1,800\n",
            "      BatchNorm2d-49           [32, 72, 28, 28]             144\n",
            "             ReLU-50           [32, 72, 28, 28]               0\n",
            "           Conv2d-51           [32, 24, 28, 28]           1,728\n",
            "      BatchNorm2d-52           [32, 24, 28, 28]              48\n",
            "_InvertedResidual-53           [32, 24, 28, 28]               0\n",
            "           Conv2d-54           [32, 72, 28, 28]           1,728\n",
            "      BatchNorm2d-55           [32, 72, 28, 28]             144\n",
            "             ReLU-56           [32, 72, 28, 28]               0\n",
            "           Conv2d-57           [32, 72, 28, 28]           1,800\n",
            "      BatchNorm2d-58           [32, 72, 28, 28]             144\n",
            "             ReLU-59           [32, 72, 28, 28]               0\n",
            "           Conv2d-60           [32, 24, 28, 28]           1,728\n",
            "      BatchNorm2d-61           [32, 24, 28, 28]              48\n",
            "_InvertedResidual-62           [32, 24, 28, 28]               0\n",
            "           Conv2d-63          [32, 144, 28, 28]           3,456\n",
            "      BatchNorm2d-64          [32, 144, 28, 28]             288\n",
            "             ReLU-65          [32, 144, 28, 28]               0\n",
            "           Conv2d-66