CIFAR_10_Object_Recognition_(ResNet50).ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "P7VUEXQAEPA7"
      },
      "outputs": [],
      "source": [
        "#!pip install kaggle"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "## Configuring the path of kaggle.json file\n",
        "\n",
        "!mkdir -p ~/.kaggle\n",
        "!cp kaggle.json ~/.kaggle/\n",
        "!chmod 600 ~/.kaggle/kaggle.json"
      ],
      "metadata": {
        "id": "eiLd3TGUFc7V"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## Dataset API\n",
        "!kaggle competitions download -c cifar-10"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aclCSWZGFc3x",
        "outputId": "82f61bf4-0871-4046-8962-1037bd2f9c19"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading cifar-10.zip to /content\n",
            "100% 713M/715M [00:06<00:00, 134MB/s]\n",
            "100% 715M/715M [00:06<00:00, 124MB/s]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Extracting the compressed dataset\n",
        "\n",
        "from zipfile import ZipFile\n",
        "\n",
        "data = '/content/cifar-10.zip'\n",
        "\n",
        "with ZipFile(data,'r') as zip:\n",
        "  zip.extractall()\n",
        "  print('The dataset has been extracted')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9Exfa-HuFc02",
        "outputId": "3c8bbb02-5e94-428c-f076-76fd5c417c58"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "The dataset has been extracted\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AxlTHFibFcyC",
        "outputId": "768e3f57-596d-4a3f-d9f5-c95dac4799f9"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "cifar-10.zip  kaggle.json  sample_data\tsampleSubmission.csv  test.7z  train.7z  trainLabels.csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "## To extract .7z file\n",
        "!pip install py7zr"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "seHiauxlFcvB",
        "outputId": "1bf53991-2f75-4d94-b14c-844be681f5a5"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting py7zr\n",
            "  Downloading py7zr-0.21.0-py3-none-any.whl (67 kB)\n",
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/67.6 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.6/67.6 kB\u001b[0m \u001b[31m3.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting texttable (from py7zr)\n",
            "  Downloading texttable-1.7.0-py2.py3-none-any.whl (10 kB)\n",
            "Collecting pycryptodomex>=3.16.0 (from py7zr)\n",
            "  Downloading pycryptodomex-3.20.0-cp35-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyzstd>=0.15.9 (from py7zr)\n",
            "  Downloading pyzstd-0.15.10-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (411 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m411.2/411.2 kB\u001b[0m \u001b[31m25.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyppmd<1.2.0,>=1.1.0 (from py7zr)\n",
            "  Downloading pyppmd-1.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (138 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m138.9/138.9 kB\u001b[0m \u001b[31m20.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pybcj<1.1.0,>=1.0.0 (from py7zr)\n",
            "  Downloading pybcj-1.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (49 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.7/49.7 kB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting multivolumefile>=0.2.3 (from py7zr)\n",
            "  Downloading multivolumefile-0.2.3-py3-none-any.whl (17 kB)\n",
            "Collecting inflate64<1.1.0,>=1.0.0 (from py7zr)\n",
            "  Downloading inflate64-1.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (93 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.1/93.1 kB\u001b[0m \u001b[31m14.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting brotli>=1.1.0 (from py7zr)\n",
            "  Downloading Brotli-1.1.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (3.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m35.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from py7zr) (5.9.5)\n",
            "Installing collected packages: texttable, brotli, pyzstd, pyppmd, pycryptodomex, pybcj, multivolumefile, inflate64, py7zr\n",
            "Successfully installed brotli-1.1.0 inflate64-1.0.0 multivolumefile-0.2.3 py7zr-0.21.0 pybcj-1.0.2 pycryptodomex-3.20.0 pyppmd-1.1.0 pyzstd-0.15.10 texttable-1.7.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import py7zr\n",
        "\n",
        "archive = py7zr.SevenZipFile('/content/train.7z', mode='r')\n",
        "archive.extractall()\n",
        "archive.close()"
      ],
      "metadata": {
        "id": "mp2iLgJAN3mW"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!ls"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Au8fWb08N3iw",
        "outputId": "6d313eac-b01c-48bf-ca77-6d9dadfbe0fe"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "cifar-10.zip  sample_data\t    test.7z  train.7z\n",
            "kaggle.json   sampleSubmission.csv  train    trainLabels.csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "##**Importing Neccessary Libraries**"
      ],
      "metadata": {
        "id": "iwTyEWINQG9i"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "from PIL import Image\n",
        "import matplotlib.pyplot as plt\n",
        "import matplotlib.image as mpimg\n",
        "from sklearn.model_selection import train_test_split"
      ],
      "metadata": {
        "id": "QKm84oC0N3gM"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "filenames = os.listdir('/content/train')\n",
        "\n",
        "print(type(filenames), len(filenames))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Agqn-LfqN3dn",
        "outputId": "68e9363a-16b4-41b4-85bc-bb2a135a0725"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'list'> 50000\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(filenames[0:5])\n",
        "print(filenames[-5:])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RWTegmfyN3bC",
        "outputId": "93264e1a-8e13-4adc-b36f-be3228247e6c"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['41310.png', '39080.png', '35059.png', '37223.png', '32461.png']\n",
            "['6303.png', '29209.png', '2058.png', '1556.png', '48333.png']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Label Processing**"
      ],
      "metadata": {
        "id": "x78jwthAR39e"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "labels_df = pd.read_csv('/content/trainLabels.csv')"
      ],
      "metadata": {
        "id": "r4JiIvy6N3YW"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "labels_df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gPcOwsRKShDD",
        "outputId": "21f140a2-330b-468b-d774-4a6babb5d947"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(50000, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "Sc7CwPLASrRr",
        "outputId": "d4b73f9b-daf8-478e-ae6f-a6ca0322fc9f"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   id       label\n",
              "0   1        frog\n",
              "1   2       truck\n",
              "2   3       truck\n",
              "3   4        deer\n",
              "4   5  automobile"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d1280511-48ca-4f45-aa0b-a956f3dd2a71\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>frog</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>truck</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>truck</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>deer</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>automobile</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d1280511-48ca-4f45-aa0b-a956f3dd2a71')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-d1280511-48ca-4f45-aa0b-a956f3dd2a71 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-d1280511-48ca-4f45-aa0b-a956f3dd2a71');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-0573fd2b-c40b-43c7-808e-08b3b8d2d073\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0573fd2b-c40b-43c7-808e-08b3b8d2d073')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-0573fd2b-c40b-43c7-808e-08b3b8d2d073 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "labels_df",
              "summary": "{\n  \"name\": \"labels_df\",\n  \"rows\": 50000,\n  \"fields\": [\n    {\n      \"column\": \"id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14433,\n        \"min\": 1,\n        \"max\": 50000,\n        \"num_unique_values\": 50000,\n        \"samples\": [\n          33554,\n          9428,\n          200\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"label\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 10,\n        \"samples\": [\n          \"dog\",\n          \"truck\",\n          \"horse\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels_df[labels_df['id']==49292]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "pN5WtmzdVlVT",
        "outputId": "2b2b65b1-d210-4b55-ea11-81523e18a002"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "          id label\n",
              "49291  49292  ship"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-cd6e0b2f-235a-42ec-814a-66c18e6ab8f7\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>49291</th>\n",
              "      <td>49292</td>\n",
              "      <td>ship</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cd6e0b2f-235a-42ec-814a-66c18e6ab8f7')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-cd6e0b2f-235a-42ec-814a-66c18e6ab8f7 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-cd6e0b2f-235a-42ec-814a-66c18e6ab8f7');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"labels_df[labels_df['id']==49292]\",\n  \"rows\": 1,\n  \"fields\": [\n    {\n      \"column\": \"id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": null,\n        \"min\": 49292,\n        \"max\": 49292,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          49292\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"label\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"ship\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels_df.tail()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "6sHmcIQOV3vr",
        "outputId": "7b2ecfc0-3459-440f-d5d4-8fac8d8429ef"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "          id       label\n",
              "49995  49996        bird\n",
              "49996  49997        frog\n",
              "49997  49998       truck\n",
              "49998  49999  automobile\n",
              "49999  50000  automobile"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-0b0b99cd-5f99-4510-906c-41b620d7223b\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>49995</th>\n",
              "      <td>49996</td>\n",
              "      <td>bird</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49996</th>\n",
              "      <td>49997</td>\n",
              "      <td>frog</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49997</th>\n",
              "      <td>49998</td>\n",
              "      <td>truck</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49998</th>\n",
              "      <td>49999</td>\n",
              "      <td>automobile</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49999</th>\n",
              "      <td>50000</td>\n",
              "      <td>automobile</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0b0b99cd-5f99-4510-906c-41b620d7223b')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-0b0b99cd-5f99-4510-906c-41b620d7223b button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-0b0b99cd-5f99-4510-906c-41b620d7223b');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-1bf3747f-8224-468a-95b7-8a285e32ed83\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-1bf3747f-8224-468a-95b7-8a285e32ed83')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-1bf3747f-8224-468a-95b7-8a285e32ed83 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"labels_df\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 49996,\n        \"max\": 50000,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          49997,\n          50000,\n          49998\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"label\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"frog\",\n          \"automobile\",\n          \"bird\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels_df['label'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eXfm5eYHV9Vw",
        "outputId": "5a9855ea-3fe5-4ec6-b214-a36a3e66b9fa"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "label\n",
              "frog          5000\n",
              "truck         5000\n",
              "deer          5000\n",
              "automobile    5000\n",
              "bird          5000\n",
              "horse         5000\n",
              "ship          5000\n",
              "cat           5000\n",
              "dog           5000\n",
              "airplane      5000\n",
              "Name: count, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels_dictionary = {'airplane':0, 'automobile':1, 'bird':2, 'cat':3, 'deer':4, 'dog':5, 'frog':6, 'horse':7, 'ship':8, 'truck':9}\n",
        "\n",
        "labels = [labels_dictionary[i] for i in labels_df['label']]"
      ],
      "metadata": {
        "id": "ngUwaRlRWFV8"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(labels[0:5])\n",
        "print(labels[-5:])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XiyDVujAWoPp",
        "outputId": "2ff582a1-2492-4b60-c5fb-41c0494f309d"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[6, 9, 9, 4, 1]\n",
            "[2, 6, 9, 1, 1]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Displaying Sample Images**"
      ],
      "metadata": {
        "id": "POxapM_AeoqU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import cv2\n",
        "from google.colab.patches import cv2_imshow\n",
        "\n",
        "img = cv2.imread('/content/train/41888.png')\n",
        "cv2_imshow(img)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49
        },
        "id": "fTVJq0uJWyq7",
        "outputId": "90ac7989-a468-49c6-a16c-63f8d8da1be9"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=32x32>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "id_list = list(labels_df['id'])\n",
        "\n",
        "print(id_list[0:5])\n",
        "print(id_list[-5:])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GbjdPCsce-wA",
        "outputId": "66d1a065-fc58-4f6c-b503-ec70e2615d4e"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[1, 2, 3, 4, 5]\n",
            "[49996, 49997, 49998, 49999, 50000]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Image Processing**"
      ],
      "metadata": {
        "id": "SL7crJoCidka"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "## Converting images to numpy arrays\n",
        "\n",
        "train_data_folder = '/content/train/'\n",
        "\n",
        "data = []\n",
        "\n",
        "for id in id_list:\n",
        "\n",
        "  image = Image.open(train_data_folder + str(id) + '.png')\n",
        "  image = np.array(image)\n",
        "  data.append(image)"
      ],
      "metadata": {
        "id": "72vNNIScfKFs"
      },
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "type(data)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cGYiHBGWjS86",
        "outputId": "29df1c2c-cb8b-478b-d7f6-7acad8bd9779"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "list"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "len(data)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gjOXE8QJlxPt",
        "outputId": "c3718c52-de7a-4309-cb33-0051d473ad78"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "50000"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "type(data[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KwB9Q1SIl9B0",
        "outputId": "c16b44f5-594c-4a3a-dcd5-ef88dbd71851"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "numpy.ndarray"
            ]
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[0].shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qvmyRAvdlz2X",
        "outputId": "fefec29c-1676-4223-e1df-ea70a30c99a7"
      },
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(32, 32, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data[0]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "3GCbfX86l3wd",
        "outputId": "472a7b16-4f25-46fa-9716-6d5d5bf52df8"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[[ 59,  62,  63],\n",
              "        [ 43,  46,  45],\n",
              "        [ 50,  48,  43],\n",
              "        ...,\n",
              "        [158, 132, 108],\n",
              "        [152, 125, 102],\n",
              "        [148, 124, 103]],\n",
              "\n",
              "       [[ 16,  20,  20],\n",
              "        [  0,   0,   0],\n",
              "        [ 18,   8,   0],\n",
              "        ...,\n",
              "        [123,  88,  55],\n",
              "        [119,  83,  50],\n",
              "        [122,  87,  57]],\n",
              "\n",
              "       [[ 25,  24,  21],\n",
              "        [ 16,   7,   0],\n",
              "        [ 49,  27,   8],\n",
              "        ...,\n",
              "        [118,  84,  50],\n",
              "        [120,  84,  50],\n",
              "        [109,  73,  42]],\n",
              "\n",
              "       ...,\n",
              "\n",
              "       [[208, 170,  96],\n",
              "        [201, 153,  34],\n",
              "        [198, 161,  26],\n",
              "        ...,\n",
              "        [160, 133,  70],\n",
              "        [ 56,  31,   7],\n",
              "        [ 53,  34,  20]],\n",
              "\n",
              "       [[180, 139,  96],\n",
              "        [173, 123,  42],\n",
              "        [186, 144,  30],\n",
              "        ...,\n",
              "        [184, 148,  94],\n",
              "        [ 97,  62,  34],\n",
              "        [ 83,  53,  34]],\n",
              "\n",
              "       [[177, 144, 116],\n",
              "        [168, 129,  94],\n",
              "        [179, 142,  87],\n",
              "        ...,\n",
              "        [216, 184, 140],\n",
              "        [151, 118,  84],\n",
              "        [123,  92,  72]]], dtype=uint8)"
            ],
            "text/html": [
              "<style>\n",
              "      .ndarray_repr .ndarray_raw_data {\n",
              "        display: none;\n",
              "      }\n",
              "      .ndarray_repr.show_array .ndarray_raw_data {\n",
              "        display: block;\n",
              "      }\n",
              "      .ndarray_repr.show_array .ndarray_image_preview {\n",
              "        display: none;\n",
              "      }\n",
              "      </style>\n",
              "      <div id=\"id-d4d4d2bd-4b62-43f0-bc83-89dbf2ba21a6\" class=\"ndarray_repr\"><pre>ndarray (32, 32, 3) <button style=\"padding: 0 2px;\">show data</button></pre><img src=\"data:image/png;base64,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\" class=\"ndarray_image_preview\" /><pre class=\"ndarray_raw_data\">array([[[ 59,  62,  63],\n",
              "        [ 43,  46,  45],\n",
              "        [ 50,  48,  43],\n",
              "        ...,\n",
              "        [158, 132, 108],\n",
              "        [152, 125, 102],\n",
              "        [148, 124, 103]],\n",
              "\n",
              "       [[ 16,  20,  20],\n",
              "        [  0,   0,   0],\n",
              "        [ 18,   8,   0],\n",
              "        ...,\n",
              "        [123,  88,  55],\n",
              "        [119,  83,  50],\n",
              "        [122,  87,  57]],\n",
              "\n",
              "       [[ 25,  24,  21],\n",
              "        [ 16,   7,   0],\n",
              "        [ 49,  27,   8],\n",
              "        ...,\n",
              "        [118,  84,  50],\n",
              "        [120,  84,  50],\n",
              "        [109,  73,  42]],\n",
              "\n",
              "       ...,\n",
              "\n",
              "       [[208, 170,  96],\n",
              "        [201, 153,  34],\n",
              "        [198, 161,  26],\n",
              "        ...,\n",
              "        [160, 133,  70],\n",
              "        [ 56,  31,   7],\n",
              "        [ 53,  34,  20]],\n",
              "\n",
              "       [[180, 139,  96],\n",
              "        [173, 123,  42],\n",
              "        [186, 144,  30],\n",
              "        ...,\n",
              "        [184, 148,  94],\n",
              "        [ 97,  62,  34],\n",
              "        [ 83,  53,  34]],\n",
              "\n",
              "       [[177, 144, 116],\n",
              "        [168, 129,  94],\n",
              "        [179, 142,  87],\n",
              "        ...,\n",
              "        [216, 184, 140],\n",
              "        [151, 118,  84],\n",
              "        [123,  92,  72]]], dtype=uint8)</pre></div><script>\n",
              "      (() => {\n",
              "      const titles = ['show data', 'hide data'];\n",
              "      let index = 0\n",
              "      document.querySelector('#id-d4d4d2bd-4b62-43f0-bc83-89dbf2ba21a6 button').onclick = (e) => {\n",
              "        document.querySelector('#id-d4d4d2bd-4b62-43f0-bc83-89dbf2ba21a6').classList.toggle('show_array');\n",
              "        index = (++index) % 2;\n",
              "        document.querySelector('#id-d4d4d2bd-4b62-43f0-bc83-89dbf2ba21a6 button').textContent = titles[index];\n",
              "        e.preventDefault();\n",
              "        e.stopPropagation();\n",
              "      }\n",
              "      })();\n",
              "    </script>"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "## Convert Image list and label list to numpy arrays\n",
        "\n",
        "X = np.array(data)\n",
        "y = np.array(labels)"
      ],
      "metadata": {
        "id": "C-7L6LRhl5yh"
      },
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(X.shape)\n",
        "print(y.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4DeA8_RymR_o",
        "outputId": "ea4e9c76-2417-4f4c-8507-9ac0221a7c5b"
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(50000, 32, 32, 3)\n",
            "(50000,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "##**Train Test Split**"
      ],
      "metadata": {
        "id": "aoPfa8HJmVEV"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2, random_state=0)"
      ],
      "metadata": {
        "id": "iLUANUlxmT9K"
      },
      "execution_count": 31,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(X.shape, X_train.shape, X_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iNtY9KrlmvB9",
        "outputId": "0573b27b-429c-482f-f4e5-d9a710cabcaa"
      },
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(50000, 32, 32, 3) (40000, 32, 32, 3) (10000, 32, 32, 3)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# scaling the data\n",
        "\n",
        "X_train_scaled = X_train/255\n",
        "\n",
        "X_test_scaled = X_test/255"
      ],
      "metadata": {
        "id": "-FdiBvM1myc0"
      },
      "execution_count": 33,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "##**Building Neural Network**"
      ],
      "metadata": {
        "id": "prq8OtRD8lZg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow import keras"
      ],
      "metadata": {
        "id": "0G3OmCOTm2pl"
      },
      "execution_count": 34,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "num_of_classes = 10\n",
        "\n",
        "## Setting up layers of Neural Network\n",
        "\n",
        "model = keras.Sequential([\n",
        "\n",
        "      keras.layers.Flatten(input_shape=(32,32,3)),\n",
        "      keras.layers.Dense(64, activation='relu'),\n",
        "      keras.layers.Dense(num_of_classes, activation='softmax')\n",
        "])"
      ],
      "metadata": {
        "id": "s_kV1NgL8i85"
      },
      "execution_count": 35,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## Compiling Neural Network\n",
        "model.compile(optimizer='adam',\n",
        "              loss='sparse_categorical_crossentropy',\n",
        "              metrics = ['acc'])"
      ],
      "metadata": {
        "id": "TMtLebjs8i5c"
      },
      "execution_count": 36,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## Training Neural Network\n",
        "model.fit(X_train_scaled, y_train, validation_split=0.1, epochs=10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "A6ABmNYA8i3J",
        "outputId": "502d311e-2607-488b-a231-a3db043dc28d"
      },
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "1125/1125 [==============================] - 5s 3ms/step - loss: 1.9442 - acc: 0.2979 - val_loss: 1.8613 - val_acc: 0.3368\n",
            "Epoch 2/10\n",
            "1125/1125 [==============================] - 4s 4ms/step - loss: 1.8079 - acc: 0.3525 - val_loss: 1.7765 - val_acc: 0.3730\n",
            "Epoch 3/10\n",
            "1125/1125 [==============================] - 4s 4ms/step - loss: 1.7576 - acc: 0.3731 - val_loss: 1.7640 - val_acc: 0.3810\n",
            "Epoch 4/10\n",
            "1125/1125 [==============================] - 4s 3ms/step - loss: 1.7299 - acc: 0.3851 - val_loss: 1.7616 - val_acc: 0.3742\n",
            "Epoch 5/10\n",
            "1125/1125 [==============================] - 3s 3ms/step - loss: 1.7128 - acc: 0.3903 - val_loss: 1.7079 - val_acc: 0.3975\n",
            "Epoch 6/10\n",
            "1125/1125 [==============================] - 3s 3ms/step - loss: 1.6979 - acc: 0.3954 - val_loss: 1.7395 - val_acc: 0.3837\n",
            "Epoch 7/10\n",
            "1125/1125 [==============================] - 3s 3ms/step - loss: 1.6894 - acc: 0.3949 - val_loss: 1.7181 - val_acc: 0.3907\n",
            "Epoch 8/10\n",
            "1125/1125 [==============================] - 4s 4ms/step - loss: 1.6794 - acc: 0.4037 - val_loss: 1.6945 - val_acc: 0.4070\n",
            "Epoch 9/10\n",
            "1125/1125 [==============================] - 5s 4ms/step - loss: 1.6757 - acc: 0.4002 - val_loss: 1.7021 - val_acc: 0.3907\n",
            "Epoch 10/10\n",
            "1125/1125 [==============================] - 3s 3ms/step - loss: 1.6645 - acc: 0.4075 - val_loss: 1.7274 - val_acc: 0.3848\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.History at 0x7a0109c949d0>"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "##**ResNet50**"
      ],
      "metadata": {
        "id": "azrsYgmr-1A6"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras import Sequential, models, layers\n",
        "from tensorflow.keras.layers import Dense, Dropout, Flatten\n",
        "from tensorflow.keras.layers import BatchNormalization\n",
        "from tensorflow.keras.models import load_model\n",
        "from tensorflow.keras.applications.resnet50 import ResNet50\n",
        "from tensorflow.keras import optimizers"
      ],
      "metadata": {
        "id": "DYhVekyt8i1v"
      },
      "execution_count": 38,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "convolutional_base = ResNet50(weights='imagenet', include_top=False, input_shape=(256,256,3))\n",
        "convolutional_base.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Np7dUNpr8iyO",
        "outputId": "7046d8cc-569d-4e97-aff8-0f772cc71a2c"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "94765736/94765736 [==============================] - 0s 0us/step\n",
            "Model: \"resnet50\"\n",
            "__________________________________________________________________________________________________\n",
            " Layer (type)                Output Shape                 Param #   Connected to                  \n",
            "==================================================================================================\n",
            " input_1 (InputLayer)        [(None, 256, 256, 3)]        0         []                            \n",
            "                                                                                                  \n",
            " conv1_pad (ZeroPadding2D)   (None, 262, 262, 3)          0         ['input_1[0][0]']             \n",
            "                                                                                                  \n",
            " conv1_conv (Conv2D)         (None, 128, 128, 64)         9472      ['conv1_pad[0][0]']           \n",
            "                                                                                                  \n",
            " conv1_bn (BatchNormalizati  (None, 128, 128, 64)         256       ['conv1_conv[0][0]']          \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv1_relu (Activation)     (None, 128, 128, 64)         0         ['conv1_bn[0][0]']            \n",
            "                                                                                                  \n",
            " pool1_pad (ZeroPadding2D)   (None, 130, 130, 64)         0         ['conv1_relu[0][0]']          \n",
            "                                                                                                  \n",
            " pool1_pool (MaxPooling2D)   (None, 64, 64, 64)           0         ['pool1_pad[0][0]']           \n",
            "                                                                                                  \n",
            " conv2_block1_1_conv (Conv2  (None, 64, 64, 64)           4160      ['pool1_pool[0][0]']          \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_bn (BatchNo  (None, 64, 64, 64)           256       ['conv2_block1_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block1_1_relu (Activ  (None, 64, 64, 64)           0         ['conv2_block1_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv2_block1_2_conv (Conv2  (None, 64, 64, 64)           36928     ['conv2_block1_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_bn (BatchNo  (None, 64, 64, 64)           256       ['conv2_block1_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block1_2_relu (Activ  (None, 64, 64, 64)           0         ['conv2_block1_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv2_block1_0_conv (Conv2  (None, 64, 64, 256)          16640     ['pool1_pool[0][0]']          \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_3_conv (Conv2  (None, 64, 64, 256)          16640     ['conv2_block1_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_0_bn (BatchNo  (None, 64, 64, 256)          1024      ['conv2_block1_0_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block1_3_bn (BatchNo  (None, 64, 64, 256)          1024      ['conv2_block1_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block1_add (Add)      (None, 64, 64, 256)          0         ['conv2_block1_0_bn[0][0]',   \n",
            "                                                                     'conv2_block1_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv2_block1_out (Activati  (None, 64, 64, 256)          0         ['conv2_block1_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_1_conv (Conv2  (None, 64, 64, 64)           16448     ['conv2_block1_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_1_bn (BatchNo  (None, 64, 64, 64)           256       ['conv2_block2_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block2_1_relu (Activ  (None, 64, 64, 64)           0         ['conv2_block2_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv2_block2_2_conv (Conv2  (None, 64, 64, 64)           36928     ['conv2_block2_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_bn (BatchNo  (None, 64, 64, 64)           256       ['conv2_block2_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block2_2_relu (Activ  (None, 64, 64, 64)           0         ['conv2_block2_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv2_block2_3_conv (Conv2  (None, 64, 64, 256)          16640     ['conv2_block2_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_3_bn (BatchNo  (None, 64, 64, 256)          1024      ['conv2_block2_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block2_add (Add)      (None, 64, 64, 256)          0         ['conv2_block1_out[0][0]',    \n",
            "                                                                     'conv2_block2_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv2_block2_out (Activati  (None, 64, 64, 256)          0         ['conv2_block2_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_1_conv (Conv2  (None, 64, 64, 64)           16448     ['conv2_block2_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_1_bn (BatchNo  (None, 64, 64, 64)           256       ['conv2_block3_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block3_1_relu (Activ  (None, 64, 64, 64)           0         ['conv2_block3_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv2_block3_2_conv (Conv2  (None, 64, 64, 64)           36928     ['conv2_block3_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_bn (BatchNo  (None, 64, 64, 64)           256       ['conv2_block3_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block3_2_relu (Activ  (None, 64, 64, 64)           0         ['conv2_block3_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv2_block3_3_conv (Conv2  (None, 64, 64, 256)          16640     ['conv2_block3_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_3_bn (BatchNo  (None, 64, 64, 256)          1024      ['conv2_block3_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv2_block3_add (Add)      (None, 64, 64, 256)          0         ['conv2_block2_out[0][0]',    \n",
            "                                                                     'conv2_block3_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv2_block3_out (Activati  (None, 64, 64, 256)          0         ['conv2_block3_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_conv (Conv2  (None, 32, 32, 128)          32896     ['conv2_block3_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block1_1_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block1_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block1_1_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block1_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block1_2_conv (Conv2  (None, 32, 32, 128)          147584    ['conv3_block1_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block1_2_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block1_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block1_2_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block1_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block1_0_conv (Conv2  (None, 32, 32, 512)          131584    ['conv2_block3_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block1_3_conv (Conv2  (None, 32, 32, 512)          66048     ['conv3_block1_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block1_0_bn (BatchNo  (None, 32, 32, 512)          2048      ['conv3_block1_0_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block1_3_bn (BatchNo  (None, 32, 32, 512)          2048      ['conv3_block1_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block1_add (Add)      (None, 32, 32, 512)          0         ['conv3_block1_0_bn[0][0]',   \n",
            "                                                                     'conv3_block1_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv3_block1_out (Activati  (None, 32, 32, 512)          0         ['conv3_block1_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_conv (Conv2  (None, 32, 32, 128)          65664     ['conv3_block1_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block2_1_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block2_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block2_1_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block2_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block2_2_conv (Conv2  (None, 32, 32, 128)          147584    ['conv3_block2_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block2_2_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block2_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block2_2_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block2_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block2_3_conv (Conv2  (None, 32, 32, 512)          66048     ['conv3_block2_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block2_3_bn (BatchNo  (None, 32, 32, 512)          2048      ['conv3_block2_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block2_add (Add)      (None, 32, 32, 512)          0         ['conv3_block1_out[0][0]',    \n",
            "                                                                     'conv3_block2_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv3_block2_out (Activati  (None, 32, 32, 512)          0         ['conv3_block2_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_conv (Conv2  (None, 32, 32, 128)          65664     ['conv3_block2_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block3_1_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block3_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block3_1_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block3_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block3_2_conv (Conv2  (None, 32, 32, 128)          147584    ['conv3_block3_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block3_2_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block3_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block3_2_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block3_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block3_3_conv (Conv2  (None, 32, 32, 512)          66048     ['conv3_block3_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block3_3_bn (BatchNo  (None, 32, 32, 512)          2048      ['conv3_block3_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block3_add (Add)      (None, 32, 32, 512)          0         ['conv3_block2_out[0][0]',    \n",
            "                                                                     'conv3_block3_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv3_block3_out (Activati  (None, 32, 32, 512)          0         ['conv3_block3_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_conv (Conv2  (None, 32, 32, 128)          65664     ['conv3_block3_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block4_1_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block4_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block4_1_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block4_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block4_2_conv (Conv2  (None, 32, 32, 128)          147584    ['conv3_block4_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block4_2_bn (BatchNo  (None, 32, 32, 128)          512       ['conv3_block4_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block4_2_relu (Activ  (None, 32, 32, 128)          0         ['conv3_block4_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv3_block4_3_conv (Conv2  (None, 32, 32, 512)          66048     ['conv3_block4_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv3_block4_3_bn (BatchNo  (None, 32, 32, 512)          2048      ['conv3_block4_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv3_block4_add (Add)      (None, 32, 32, 512)          0         ['conv3_block3_out[0][0]',    \n",
            "                                                                     'conv3_block4_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv3_block4_out (Activati  (None, 32, 32, 512)          0         ['conv3_block4_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_conv (Conv2  (None, 16, 16, 256)          131328    ['conv3_block4_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block1_1_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block1_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block1_1_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block1_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block1_2_conv (Conv2  (None, 16, 16, 256)          590080    ['conv4_block1_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block1_2_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block1_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block1_2_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block1_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block1_0_conv (Conv2  (None, 16, 16, 1024)         525312    ['conv3_block4_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block1_3_conv (Conv2  (None, 16, 16, 1024)         263168    ['conv4_block1_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block1_0_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block1_0_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block1_3_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block1_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block1_add (Add)      (None, 16, 16, 1024)         0         ['conv4_block1_0_bn[0][0]',   \n",
            "                                                                     'conv4_block1_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv4_block1_out (Activati  (None, 16, 16, 1024)         0         ['conv4_block1_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_1_conv (Conv2  (None, 16, 16, 256)          262400    ['conv4_block1_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block2_1_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block2_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block2_1_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block2_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block2_2_conv (Conv2  (None, 16, 16, 256)          590080    ['conv4_block2_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block2_2_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block2_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block2_2_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block2_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block2_3_conv (Conv2  (None, 16, 16, 1024)         263168    ['conv4_block2_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block2_3_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block2_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block2_add (Add)      (None, 16, 16, 1024)         0         ['conv4_block1_out[0][0]',    \n",
            "                                                                     'conv4_block2_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv4_block2_out (Activati  (None, 16, 16, 1024)         0         ['conv4_block2_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_1_conv (Conv2  (None, 16, 16, 256)          262400    ['conv4_block2_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block3_1_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block3_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block3_1_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block3_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block3_2_conv (Conv2  (None, 16, 16, 256)          590080    ['conv4_block3_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block3_2_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block3_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block3_2_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block3_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block3_3_conv (Conv2  (None, 16, 16, 1024)         263168    ['conv4_block3_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block3_3_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block3_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block3_add (Add)      (None, 16, 16, 1024)         0         ['conv4_block2_out[0][0]',    \n",
            "                                                                     'conv4_block3_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv4_block3_out (Activati  (None, 16, 16, 1024)         0         ['conv4_block3_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_1_conv (Conv2  (None, 16, 16, 256)          262400    ['conv4_block3_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block4_1_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block4_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block4_1_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block4_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block4_2_conv (Conv2  (None, 16, 16, 256)          590080    ['conv4_block4_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block4_2_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block4_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block4_2_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block4_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block4_3_conv (Conv2  (None, 16, 16, 1024)         263168    ['conv4_block4_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block4_3_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block4_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block4_add (Add)      (None, 16, 16, 1024)         0         ['conv4_block3_out[0][0]',    \n",
            "                                                                     'conv4_block4_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv4_block4_out (Activati  (None, 16, 16, 1024)         0         ['conv4_block4_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_1_conv (Conv2  (None, 16, 16, 256)          262400    ['conv4_block4_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block5_1_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block5_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block5_1_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block5_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block5_2_conv (Conv2  (None, 16, 16, 256)          590080    ['conv4_block5_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block5_2_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block5_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block5_2_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block5_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block5_3_conv (Conv2  (None, 16, 16, 1024)         263168    ['conv4_block5_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block5_3_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block5_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block5_add (Add)      (None, 16, 16, 1024)         0         ['conv4_block4_out[0][0]',    \n",
            "                                                                     'conv4_block5_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv4_block5_out (Activati  (None, 16, 16, 1024)         0         ['conv4_block5_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_1_conv (Conv2  (None, 16, 16, 256)          262400    ['conv4_block5_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block6_1_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block6_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block6_1_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block6_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block6_2_conv (Conv2  (None, 16, 16, 256)          590080    ['conv4_block6_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block6_2_bn (BatchNo  (None, 16, 16, 256)          1024      ['conv4_block6_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block6_2_relu (Activ  (None, 16, 16, 256)          0         ['conv4_block6_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv4_block6_3_conv (Conv2  (None, 16, 16, 1024)         263168    ['conv4_block6_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv4_block6_3_bn (BatchNo  (None, 16, 16, 1024)         4096      ['conv4_block6_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv4_block6_add (Add)      (None, 16, 16, 1024)         0         ['conv4_block5_out[0][0]',    \n",
            "                                                                     'conv4_block6_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv4_block6_out (Activati  (None, 16, 16, 1024)         0         ['conv4_block6_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_1_conv (Conv2  (None, 8, 8, 512)            524800    ['conv4_block6_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block1_1_bn (BatchNo  (None, 8, 8, 512)            2048      ['conv5_block1_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block1_1_relu (Activ  (None, 8, 8, 512)            0         ['conv5_block1_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv5_block1_2_conv (Conv2  (None, 8, 8, 512)            2359808   ['conv5_block1_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block1_2_bn (BatchNo  (None, 8, 8, 512)            2048      ['conv5_block1_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block1_2_relu (Activ  (None, 8, 8, 512)            0         ['conv5_block1_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv5_block1_0_conv (Conv2  (None, 8, 8, 2048)           2099200   ['conv4_block6_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block1_3_conv (Conv2  (None, 8, 8, 2048)           1050624   ['conv5_block1_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block1_0_bn (BatchNo  (None, 8, 8, 2048)           8192      ['conv5_block1_0_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block1_3_bn (BatchNo  (None, 8, 8, 2048)           8192      ['conv5_block1_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block1_add (Add)      (None, 8, 8, 2048)           0         ['conv5_block1_0_bn[0][0]',   \n",
            "                                                                     'conv5_block1_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv5_block1_out (Activati  (None, 8, 8, 2048)           0         ['conv5_block1_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_1_conv (Conv2  (None, 8, 8, 512)            1049088   ['conv5_block1_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block2_1_bn (BatchNo  (None, 8, 8, 512)            2048      ['conv5_block2_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block2_1_relu (Activ  (None, 8, 8, 512)            0         ['conv5_block2_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv5_block2_2_conv (Conv2  (None, 8, 8, 512)            2359808   ['conv5_block2_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block2_2_bn (BatchNo  (None, 8, 8, 512)            2048      ['conv5_block2_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block2_2_relu (Activ  (None, 8, 8, 512)            0         ['conv5_block2_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv5_block2_3_conv (Conv2  (None, 8, 8, 2048)           1050624   ['conv5_block2_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block2_3_bn (BatchNo  (None, 8, 8, 2048)           8192      ['conv5_block2_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block2_add (Add)      (None, 8, 8, 2048)           0         ['conv5_block1_out[0][0]',    \n",
            "                                                                     'conv5_block2_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv5_block2_out (Activati  (None, 8, 8, 2048)           0         ['conv5_block2_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_1_conv (Conv2  (None, 8, 8, 512)            1049088   ['conv5_block2_out[0][0]']    \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block3_1_bn (BatchNo  (None, 8, 8, 512)            2048      ['conv5_block3_1_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block3_1_relu (Activ  (None, 8, 8, 512)            0         ['conv5_block3_1_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv5_block3_2_conv (Conv2  (None, 8, 8, 512)            2359808   ['conv5_block3_1_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block3_2_bn (BatchNo  (None, 8, 8, 512)            2048      ['conv5_block3_2_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block3_2_relu (Activ  (None, 8, 8, 512)            0         ['conv5_block3_2_bn[0][0]']   \n",
            " ation)                                                                                           \n",
            "                                                                                                  \n",
            " conv5_block3_3_conv (Conv2  (None, 8, 8, 2048)           1050624   ['conv5_block3_2_relu[0][0]'] \n",
            " D)                                                                                               \n",
            "                                                                                                  \n",
            " conv5_block3_3_bn (BatchNo  (None, 8, 8, 2048)           8192      ['conv5_block3_3_conv[0][0]'] \n",
            " rmalization)                                                                                     \n",
            "                                                                                                  \n",
            " conv5_block3_add (Add)      (None, 8, 8, 2048)           0         ['conv5_block2_out[0][0]',    \n",
            "                                                                     'conv5_block3_3_bn[0][0]']   \n",
            "                                                                                                  \n",
            " conv5_block3_out (Activati  (None, 8, 8, 2048)           0         ['conv5_block3_add[0][0]']    \n",
            " on)                                                                                              \n",
            "                                                                                                  \n",
            "==================================================================================================\n",
            "Total params: 23587712 (89.98 MB)\n",
            "Trainable params: 23534592 (89.78 MB)\n",
            "Non-trainable params: 53120 (207.50 KB)\n",
            "__________________________________________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "num_of_classes = 10\n",
        "\n",
        "model = models.Sequential()\n",
        "model.add(layers.UpSampling2D((2,2)))\n",
        "model.add(layers.UpSampling2D((2,2)))\n",
        "model.add(layers.UpSampling2D((2,2)))\n",
        "model.add(convolutional_base)\n",
        "model.add(layers.Flatten())\n",
        "model.add(layers.BatchNormalization())\n",
        "model.add(layers.Dense(128, activation='relu'))\n",
        "model.add(layers.Dropout(0.5))\n",
        "model.add(layers.BatchNormalization())\n",
        "model.add(layers.Dense(64, activation='relu'))\n",
        "model.add(layers.Dropout(0.5))\n",
        "model.add(layers.BatchNormalization())\n",
        "model.add(layers.Dense(num_of_classes, activation='softmax')) #Output layerr"
      ],
      "metadata": {
        "id": "Dns8cWx7AaDZ"
      },
      "execution_count": 40,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(optimizer=optimizers.\n",
        "              RMSprop(learning_rate=2e-5),\n",
        "              loss='sparse_categorical_crossentropy',\n",
        "              metrics = ['acc'])"
      ],
      "metadata": {
        "id": "Lrc7c0uOGXS1"
      },
      "execution_count": 41,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(X_train_scaled, y_train, validation_split=0.1, epochs=10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "siRKoEBzGXPI",
        "outputId": "607a0d84-c04c-47ec-8c4d-f21775a8504c"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "1125/1125 [==============================] - 490s 400ms/step - loss: 1.6727 - acc: 0.4420 - val_loss: 0.8837 - val_acc: 0.7550\n",
            "Epoch 2/10\n",
            "1125/1125 [==============================] - 459s 408ms/step - loss: 1.0049 - acc: 0.7007 - val_loss: 0.5116 - val_acc: 0.8723\n",
            "Epoch 3/10\n",
            "1125/1125 [==============================] - 452s 402ms/step - loss: 0.7357 - acc: 0.8057 - val_loss: 0.3681 - val_acc: 0.9143\n",
            "Epoch 4/10\n",
            "1125/1125 [==============================] - 452s 402ms/step - loss: 0.5742 - acc: 0.8648 - val_loss: 0.3034 - val_acc: 0.9250\n",
            "Epoch 5/10\n",
            "1125/1125 [==============================] - 458s 407ms/step - loss: 0.4517 - acc: 0.9046 - val_loss: 0.2615 - val_acc: 0.9342\n",
            "Epoch 6/10\n",
            "1125/1125 [==============================] - 451s 401ms/step - loss: 0.3579 - acc: 0.9314 - val_loss: 0.2386 - val_acc: 0.9440\n",
            "Epoch 7/10\n",
            "1125/1125 [==============================] - 458s 407ms/step - loss: 0.2840 - acc: 0.9522 - val_loss: 0.2282 - val_acc: 0.9417\n",
            "Epoch 8/10\n",
            "1125/1125 [==============================] - 459s 408ms/step - loss: 0.2407 - acc: 0.9591 - val_loss: 0.2278 - val_acc: 0.9420\n",
            "Epoch 9/10\n",
            "1125/1125 [==============================] - 454s 403ms/step - loss: 0.1987 - acc: 0.9705 - val_loss: 0.2163 - val_acc: 0.9410\n",
            "Epoch 10/10\n",
            "1125/1125 [==============================] - 463s 411ms/step - loss: 0.1706 - acc: 0.9757 - val_loss: 0.2157 - val_acc: 0.9408\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "loss, accuracy = model.evaluate(X_test_scaled, y_test)\n",
        "print('Test Accuracy: ', accuracy)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8sP8rP_NGXM4",
        "outputId": "28400dad-2553-41cd-9c79-e83a2f82bda7"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "313/313 [==============================] - 42s 126ms/step - loss: 0.2165 - acc: 0.9416\n",
            "Test Accuracy:  0.9416000247001648\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "loss, accuracy = model.evaluate(X_test_scaled, y_test)\n",
        "print('Test Loss: ', loss)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_984eSVyGXKG",
        "outputId": "42ab0d73-7fe9-487e-e25c-761481b61e2b"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "313/313 [==============================] - 37s 117ms/step - loss: 0.2165 - acc: 0.9416\n",
            "Test Loss:  0.2164798527956009\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "h = history\n",
        "\n",
        "# plot the loss value\n",
        "plt.plot(h.history['loss'], label='train loss')\n",
        "plt.plot(h.history['val_loss'], label='validation loss')\n",
        "plt.legend()\n",
        "plt.show()\n",
        "\n",
        "# plot the accuracy value\n",
        "plt.plot(h.history['acc'], label='train accuracy')\n",
        "plt.plot(h.history['val_acc'], label='validation accuracy')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 847
        },
        "id": "zTGuxruYe-8G",
        "outputId": "d8dab739-31cc-4d6f-bdc6-26df6441ac3c"
      },
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}