Last active
May 15, 2021 04:33
-
-
Save hugozanini/4ee1a77b90f4ec6e9d4b0d3aa1506a3e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"name": "Publishing.ipynb", | |
"provenance": [] | |
}, | |
"kernelspec": { | |
"name": "python3", | |
"display_name": "Python 3" | |
} | |
}, | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "sGtfi97VCMOp" | |
}, | |
"source": [ | |
"Here we're going to run the code through a loop that waits for checkpoints to evaluate. Once the evaluation finishes, you're going to see the message:\n", | |
"\n", | |
"`INFO:tensorflow:Waiting for new checkpoint at /content/training/`\n", | |
"\n", | |
"Then you can stop the cell\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"metadata": { | |
"colab": { | |
"base_uri": "https://localhost:8080/" | |
}, | |
"id": "NR_ASWHFRvEt", | |
"outputId": "0d15f083-bf96-4090-c178-06a7ed4205dc" | |
}, | |
"source": [ | |
"!python /content/models/research/object_detection/model_main_tf2.py \\\r\n", | |
" --pipeline_config_path={pipeline_config_path} \\\r\n", | |
" --model_dir={model_dir} \\\r\n", | |
" --checkpoint_dir={model_dir} " | |
], | |
"execution_count": null, | |
"outputs": [ | |
{ | |
"output_type": "stream", | |
"text": [ | |
"INFO:tensorflow:Performing evaluation on 89 images.\n", | |
"I1220 17:34:19.304409 139900847355776 coco_evaluation.py:293] Performing evaluation on 89 images.\n", | |
"creating index...\n", | |
"index created!\n", | |
"INFO:tensorflow:Loading and preparing annotation results...\n", | |
"I1220 17:34:19.304893 139900847355776 coco_tools.py:116] Loading and preparing annotation results...\n", | |
"INFO:tensorflow:DONE (t=0.00s)\n", | |
"I1220 17:34:19.308917 139900847355776 coco_tools.py:138] DONE (t=0.00s)\n", | |
"creating index...\n", | |
"index created!\n", | |
"Running per image evaluation...\n", | |
"Evaluate annotation type *bbox*\n", | |
"DONE (t=0.42s).\n", | |
"Accumulating evaluation results...\n", | |
"DONE (t=0.05s).\n", | |
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.222\n", | |
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.405\n", | |
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.221\n", | |
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000\n", | |
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.003\n", | |
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.239\n", | |
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.293\n", | |
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.414\n", | |
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.514\n", | |
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000\n", | |
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.067\n", | |
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.543\n", | |
"INFO:tensorflow:Eval metrics at step 7000\n", | |
"I1220 17:34:19.793375 139900847355776 model_lib_v2.py:954] Eval metrics at step 7000\n", | |
"INFO:tensorflow:\t+ Loss/localization_loss: 0.345804\n", | |
"INFO:tensorflow:\t+ Loss/classification_loss: 1.496982\n", | |
"INFO:tensorflow:\t+ Loss/regularization_loss: 0.130125\n", | |
"INFO:tensorflow:\t+ Loss/total_loss: 1.972911\n", | |
"INFO:tensorflow:Waiting for new checkpoint at /content/training/\n" | |
], | |
"name": "stdout" | |
} | |
] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I want to know that the AP did not exceed 50%. Is this normal?