show_dataset.ipynb

show_dataset.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/daniel-falk/689c018cb627d3a4c0cfe616ec85208b/show_dataset.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install deeplake[enterprise]"
      ],
      "metadata": {
        "id": "FTVVJmpgd_Fg"
      },
      "id": "FTVVJmpgd_Fg",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!activeloop login -t <KEY>"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3I0w5kMYeWql",
        "outputId": "1a48bffd-67cd-4e1a-d624-6846a4a5ce11"
      },
      "id": "3I0w5kMYeWql",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Successfully logged in to Activeloop.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import deeplake\n",
        "\n",
        "ds_in = deeplake.load(\n",
        "'hub://fixedit/object_det_val'\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_FpKr1xi5B1z",
        "outputId": "aa18bc0f-9205-4f1c-fdf5-0a99737c5825"
      },
      "id": "_FpKr1xi5B1z",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/fixedit/object_det_val\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "|"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "hub://fixedit/object_det_val loaded successfully.\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\r \r\r\r"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "ds_in.tensors"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vckWgVvP9RR4",
        "outputId": "8b6b3bdf-4cbd-4f23-8be6-00154f2e3789"
      },
      "id": "vckWgVvP9RR4",
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'boxes': Tensor(key='boxes'),\n",
              " 'categories': Tensor(key='categories'),\n",
              " 'images': Tensor(key='images')}"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "ds_out = deeplake.like('./outds', ds_in, overwrite=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hueIqgEr5T-Q",
        "outputId": "01018b16-23f9-446c-e05e-37221095f216"
      },
      "id": "hueIqgEr5T-Q",
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "./outds loaded successfully.\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\r\r\r\r"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "new_ids = [100, 2, 101, 233, 0, 10, 1]\n",
        "small_view = ds_in[new_ids]"
      ],
      "metadata": {
        "id": "IMyYkvvZ7_a3"
      },
      "id": "IMyYkvvZ7_a3",
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "\n",
        "@deeplake.compute\n",
        "def flip_vertical(sample_in, sample_out):\n",
        "    sample_out.append({\n",
        "        'categories': sample_in.categories.numpy(),\n",
        "        'boxes': sample_in.boxes.numpy(),\n",
        "        'images': np.flip(sample_in.images.numpy(), axis = 0)\n",
        "    })\n",
        "\n",
        "    return sample_out"
      ],
      "metadata": {
        "id": "66QuYthy82DQ"
      },
      "id": "66QuYthy82DQ",
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "flip_vertical().eval(small_view, ds_out, num_workers = 2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UF9UNsV-9aik",
        "outputId": "608075cc-16d3-4a02-a4e3-277f35a192fb"
      },
      "id": "UF9UNsV-9aik",
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Evaluating flip_vertical: 100%|██████████| 7/7 [00:19<00:00"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Synchronizing class labels...\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\n",
            "Evaluating class_label_sync: 100%|██████████| 7/7 [00:00<00:00\n",
            "Evaluating flip_vertical: 100%|██████████| 7/7 [00:20<00:00\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "small_view.categories.numpy()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7BbTB_X39iJk",
        "outputId": "ab964a1c-5a8d-431c-8c6a-19466c25f654"
      },
      "id": "7BbTB_X39iJk",
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[1],\n",
              "       [1],\n",
              "       [1],\n",
              "       [0],\n",
              "       [1],\n",
              "       [1],\n",
              "       [1]], dtype=uint32)"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "ds_out.categories.numpy()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DrYahkUD9uwL",
        "outputId": "c14e38dc-1145-4b27-9c83-bb5858df88fc"
      },
      "id": "DrYahkUD9uwL",
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[1],\n",
              "       [1],\n",
              "       [1],\n",
              "       [0],\n",
              "       [1],\n",
              "       [1],\n",
              "       [1]], dtype=uint32)"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.0"
    },
    "colab": {
      "provenance": [],
      "include_colab_link": true
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}