model_training_pipeline.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Copy of TESTINGTESTING of Cyclone_intensity_detection.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyOuk2UpCSOJBuMoBkscaDz2",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/cycloneintensity/CrossKnotHacks-Cyclonet/blob/main/model_training_pipeline.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        " for dataset access mail to verma.sshubam@gmail.com"
      ],
      "metadata": {
        "id": "Eb2GWr9CPAjR"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "import torch.nn as nn\n",
        "import torchvision\n",
        "from torchvision import transforms\n",
        "from torchsummary import summary\n",
        "import torchvision.transforms as transforms\n",
        "from torch.utils.data import Dataset, DataLoader\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import cv2"
      ],
      "metadata": {
        "id": "oXNPb97z19ti"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip cyclone_ds.zip"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yzLKq_aGhhzQ",
        "outputId": "81f52a2f-f4c3-4592-aa0e-8155eb18e67a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Archive:  cyclone_ds.zip\n",
            "   creating: CYCLONE_DATASET_INFRARED/\n",
            "  inflating: CYCLONE_DATASET_INFRARED/63.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/77.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/85(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/62.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/74.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/60.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/48.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/64(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/42(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/61(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/57(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/40(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/49(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/34(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/45(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/49.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/61.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/75.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/74(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/59.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/65.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/63(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/40(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/.DS_Store  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/59(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/50(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/47(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/33(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/36(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/64.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/70.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/58.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/99.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/82(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/98.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/73.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/67.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/28.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/32(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/101.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/115.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/51(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/44(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/128.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/48(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/67(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/35(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/102.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/86(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/84(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/106.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/112.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/39.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/35(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/48(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/53(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/30(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/44(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/77(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/111.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/46(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/69(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/38.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/60(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/35(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/35.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/48(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/53(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/44(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/65(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/47(4).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/60(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/34.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/36.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/81(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/37.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/33.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/27.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/83(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/86(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/32.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/30.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/46(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/119.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/58(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/65(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/43(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/53(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/45(4).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/118.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/31.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/25.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/42.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/56.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/81.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/94.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/57.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/43.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/55.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/41.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/69.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/74(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/82.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/63(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/45(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/50(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/59(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/47(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/33(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/36(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/55(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/68.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/40.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/54.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/50.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/44.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/87.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/64(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/36(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/61(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/47(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/59(3).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/57(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/49(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/40(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/45(2).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/86.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/52(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/45.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/51.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/47.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/53.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/85(1).jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/84.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/85.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/52.jpg  \n",
            "  inflating: CYCLONE_DATASET_INFRARED/46.jpg  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "pd.read_csv('Untitled spreadsheet - Sheet1 (1).csv')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 2267
        },
        "id": "a6ZKW1F4zvGb",
        "outputId": "811189bf-6e95-4f43-fb62-2c637b0b141c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      img_name  label\n",
              "0       25.jpg     25\n",
              "1       27.jpg     27\n",
              "2       28.jpg     28\n",
              "3       30.jpg     30\n",
              "4    30(1).jpg     30\n",
              "..         ...    ...\n",
              "131    112.jpg    112\n",
              "132    115.jpg    115\n",
              "133    118.jpg    118\n",
              "134    119.jpg    119\n",
              "135    128.jpg    128\n",
              "\n",
              "[136 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-bee0d4a1-80c2-48fd-a7ab-2fa06ee0a6bd\">\n",
              "    <div 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>img_name</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>25.jpg</td>\n",
              "      <td>25</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>27.jpg</td>\n",
              "      <td>27</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>28.jpg</td>\n",
              "      <td>28</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>30.jpg</td>\n",
              "      <td>30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>30(1).jpg</td>\n",
              "      <td>30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>131</th>\n",
              "      <td>112.jpg</td>\n",
              "      <td>112</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>132</th>\n",
              "      <td>115.jpg</td>\n",
              "      <td>115</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>133</th>\n",
              "      <td>118.jpg</td>\n",
              "      <td>118</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>134</th>\n",
              "      <td>119.jpg</td>\n",
              "      <td>119</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>135</th>\n",
              "      <td>128.jpg</td>\n",
              "      <td>128</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>136 rows × 2 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-bee0d4a1-80c2-48fd-a7ab-2fa06ee0a6bd')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-bee0d4a1-80c2-48fd-a7ab-2fa06ee0a6bd 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-bee0d4a1-80c2-48fd-a7ab-2fa06ee0a6bd');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "TRAIN_DIR = '/content/CYCLONE_DATASET_INFRARED'\n",
        "ROOT_DIR = '/content'"
      ],
      "metadata": {
        "id": "DsOvCmiy1OOg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def get_train_file_path(id):\n",
        "    return f\"{TRAIN_DIR}/{id}\"     "
      ],
      "metadata": {
        "id": "RT6DFctm1J1R"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(f\"{ROOT_DIR}/Untitled spreadsheet - Sheet1 (1).csv\")\n",
        "df['file_path'] = df['img_name'].apply(get_train_file_path)"
      ],
      "metadata": {
        "id": "8s8GwUZW1Wte"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "E62LkLyA1qLl",
        "outputId": "5b5d7834-c8da-4901-d15b-763f924f8382"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      img_name  label                                    file_path\n",
              "0       25.jpg     25     /content/CYCLONE_DATASET_INFRARED/25.jpg\n",
              "1       27.jpg     27     /content/CYCLONE_DATASET_INFRARED/27.jpg\n",
              "2       28.jpg     28     /content/CYCLONE_DATASET_INFRARED/28.jpg\n",
              "3       30.jpg     30     /content/CYCLONE_DATASET_INFRARED/30.jpg\n",
              "4    30(1).jpg     30  /content/CYCLONE_DATASET_INFRARED/30(1).jpg\n",
              "..         ...    ...                                          ...\n",
              "131    112.jpg    112    /content/CYCLONE_DATASET_INFRARED/112.jpg\n",
              "132    115.jpg    115    /content/CYCLONE_DATASET_INFRARED/115.jpg\n",
              "133    118.jpg    118    /content/CYCLONE_DATASET_INFRARED/118.jpg\n",
              "134    119.jpg    119    /content/CYCLONE_DATASET_INFRARED/119.jpg\n",
              "135    128.jpg    128    /content/CYCLONE_DATASET_INFRARED/128.jpg\n",
              "\n",
              "[136 rows x 3 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-6597d331-c1c6-4669-8253-34c15c31f700\">\n",
              "    <div 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>img_name</th>\n",
              "      <th>label</th>\n",
              "      <th>file_path</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>25.jpg</td>\n",
              "      <td>25</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/25.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>27.jpg</td>\n",
              "      <td>27</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/27.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>28.jpg</td>\n",
              "      <td>28</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/28.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>30.jpg</td>\n",
              "      <td>30</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/30.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>30(1).jpg</td>\n",
              "      <td>30</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/30(1).jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>131</th>\n",
              "      <td>112.jpg</td>\n",
              "      <td>112</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/112.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>132</th>\n",
              "      <td>115.jpg</td>\n",
              "      <td>115</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/115.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>133</th>\n",
              "      <td>118.jpg</td>\n",
              "      <td>118</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/118.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>134</th>\n",
              "      <td>119.jpg</td>\n",
              "      <td>119</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/119.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>135</th>\n",
              "      <td>128.jpg</td>\n",
              "      <td>128</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/128.jpg</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>136 rows × 3 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6597d331-c1c6-4669-8253-34c15c31f700')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-6597d331-c1c6-4669-8253-34c15c31f700 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-6597d331-c1c6-4669-8253-34c15c31f700');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 85
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.drop([df.index[32] , df.index[116], df.index[124]])"
      ],
      "metadata": {
        "id": "uvZ9YtDktD_I"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "EYN4anakuC_A",
        "outputId": "5bf1b7a6-bf51-4f80-f6bb-7594d853a9db"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      img_name  label                                    file_path\n",
              "0       25.jpg     25     /content/CYCLONE_DATASET_INFRARED/25.jpg\n",
              "1       27.jpg     27     /content/CYCLONE_DATASET_INFRARED/27.jpg\n",
              "2       28.jpg     28     /content/CYCLONE_DATASET_INFRARED/28.jpg\n",
              "3       30.jpg     30     /content/CYCLONE_DATASET_INFRARED/30.jpg\n",
              "4    30(1).jpg     30  /content/CYCLONE_DATASET_INFRARED/30(1).jpg\n",
              "..         ...    ...                                          ...\n",
              "131    112.jpg    112    /content/CYCLONE_DATASET_INFRARED/112.jpg\n",
              "132    115.jpg    115    /content/CYCLONE_DATASET_INFRARED/115.jpg\n",
              "133    118.jpg    118    /content/CYCLONE_DATASET_INFRARED/118.jpg\n",
              "134    119.jpg    119    /content/CYCLONE_DATASET_INFRARED/119.jpg\n",
              "135    128.jpg    128    /content/CYCLONE_DATASET_INFRARED/128.jpg\n",
              "\n",
              "[133 rows x 3 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-5b543211-1999-4052-aaab-dd1d39fedc5c\">\n",
              "    <div 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>img_name</th>\n",
              "      <th>label</th>\n",
              "      <th>file_path</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>25.jpg</td>\n",
              "      <td>25</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/25.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>27.jpg</td>\n",
              "      <td>27</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/27.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>28.jpg</td>\n",
              "      <td>28</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/28.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>30.jpg</td>\n",
              "      <td>30</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/30.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>30(1).jpg</td>\n",
              "      <td>30</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/30(1).jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>131</th>\n",
              "      <td>112.jpg</td>\n",
              "      <td>112</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/112.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>132</th>\n",
              "      <td>115.jpg</td>\n",
              "      <td>115</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/115.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>133</th>\n",
              "      <td>118.jpg</td>\n",
              "      <td>118</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/118.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>134</th>\n",
              "      <td>119.jpg</td>\n",
              "      <td>119</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/119.jpg</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>135</th>\n",
              "      <td>128.jpg</td>\n",
              "      <td>128</td>\n",
              "      <td>/content/CYCLONE_DATASET_INFRARED/128.jpg</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>133 rows × 3 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5b543211-1999-4052-aaab-dd1d39fedc5c')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-5b543211-1999-4052-aaab-dd1d39fedc5c 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-5b543211-1999-4052-aaab-dd1d39fedc5c');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 87
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.keys"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SV25DzpB8vqp",
        "outputId": "bcca1cea-6319-4a1b-d259-0262c917d69e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<bound method NDFrame.keys of       img_name  label                                    file_path\n",
              "0       25.jpg     25     /content/CYCLONE_DATASET_INFRARED/25.jpg\n",
              "1       27.jpg     27     /content/CYCLONE_DATASET_INFRARED/27.jpg\n",
              "2       28.jpg     28     /content/CYCLONE_DATASET_INFRARED/28.jpg\n",
              "3       30.jpg     30     /content/CYCLONE_DATASET_INFRARED/30.jpg\n",
              "4    30(1).jpg     30  /content/CYCLONE_DATASET_INFRARED/30(1).jpg\n",
              "..         ...    ...                                          ...\n",
              "131    112.jpg    112    /content/CYCLONE_DATASET_INFRARED/112.jpg\n",
              "132    115.jpg    115    /content/CYCLONE_DATASET_INFRARED/115.jpg\n",
              "133    118.jpg    118    /content/CYCLONE_DATASET_INFRARED/118.jpg\n",
              "134    119.jpg    119    /content/CYCLONE_DATASET_INFRARED/119.jpg\n",
              "135    128.jpg    128    /content/CYCLONE_DATASET_INFRARED/128.jpg\n",
              "\n",
              "[133 rows x 3 columns]>"
            ]
          },
          "metadata": {},
          "execution_count": 88
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.index"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JodM8I5qB6cT",
        "outputId": "e6d51fd5-22d2-486f-fe8e-a2c35ac0e8f4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Int64Index([  0,   1,   2,   3,   4,   5,   6,   7,   8,   9,\n",
              "            ...\n",
              "            126, 127, 128, 129, 130, 131, 132, 133, 134, 135],\n",
              "           dtype='int64', length=133)"
            ]
          },
          "metadata": {},
          "execution_count": 89
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class CycloneDataset(Dataset):\n",
        "  def __init__(self, df, transforms=None):\n",
        "    self.df = df\n",
        "    self.file_names = df['file_path'].values\n",
        "    self.labels = df['label'].values\n",
        "    self.transforms = transforms\n",
        "        \n",
        "  def __len__(self):\n",
        "    return len(self.df)\n",
        "\n",
        "#transforms.compose reminder\n",
        " \n",
        "  def __getitem__(self, index):\n",
        "    img_path = self.file_names[index]\n",
        "    img = cv2.imread(img_path)\n",
        "    img = np.array(img)\n",
        "    totensor = transforms.ToTensor()\n",
        "    img = totensor(img)\n",
        "    resize = transforms.Resize(size=(250, 250))\n",
        "    img = resize(img)\n",
        "    flip = transforms.RandomHorizontalFlip(p = 0.5)\n",
        "    img = flip(img)\n",
        "    label = self.labels[index]\n",
        "        \n",
        "    if self.transforms:\n",
        "      img = self.transforms(image=img)[\"image\"]\n",
        "            \n",
        "    return img, torch.tensor(label, dtype=torch.long).float()"
      ],
      "metadata": {
        "id": "wgwuDdktch5U"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "dataset = CycloneDataset(df)"
      ],
      "metadata": {
        "id": "gSvtudSr7IBP"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8ncFcz9x7OVo",
        "outputId": "22709a0a-1018-434a-cece-af0bee74889d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<__main__.CycloneDataset at 0x7fba668ad510>"
            ]
          },
          "metadata": {},
          "execution_count": 93
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset = CycloneDataset(df)\n",
        "data_loader = DataLoader(dataset, batch_size=4, shuffle=True)"
      ],
      "metadata": {
        "id": "bUKqIRpM-dgw"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_loader"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rHgdV8jT-4Vc",
        "outputId": "8493f08c-97e0-4157-a29f-aa1bf290eeac"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<torch.utils.data.dataloader.DataLoader at 0x7fba671bd950>"
            ]
          },
          "metadata": {},
          "execution_count": 95
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np"
      ],
      "metadata": {
        "id": "LKXHENbuNtbs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# for view_img, view_label in data_loader:\n",
        "#   print(view_img, view_label)"
      ],
      "metadata": {
        "id": "ejOPe1mtKgHD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "dataset[131]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NnruwSQLptIH",
        "outputId": "e752cda8-8f0c-47e3-f16f-87487de511f7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(tensor([[[0.0586, 0.0919, 0.0937,  ..., 0.3122, 0.3959, 0.6549],\n",
              "          [0.0615, 0.0888, 0.0908,  ..., 0.3367, 0.4274, 0.6604],\n",
              "          [0.0699, 0.0814, 0.0817,  ..., 0.3306, 0.4435, 0.6610],\n",
              "          ...,\n",
              "          [0.2446, 0.2799, 0.2681,  ..., 0.2422, 0.3200, 0.6517],\n",
              "          [0.2574, 0.2914, 0.2837,  ..., 0.1351, 0.1860, 0.6763],\n",
              "          [0.2032, 0.2301, 0.2356,  ..., 0.2539, 0.2850, 0.7164]],\n",
              " \n",
              "         [[0.1048, 0.1336, 0.1325,  ..., 0.9440, 0.8998, 0.9758],\n",
              "          [0.1021, 0.1269, 0.1247,  ..., 0.9553, 0.9186, 0.9782],\n",
              "          [0.1091, 0.1183, 0.1137,  ..., 0.9339, 0.9187, 0.9776],\n",
              "          ...,\n",
              "          [0.6178, 0.6697, 0.6799,  ..., 0.5661, 0.6001, 0.8764],\n",
              "          [0.6741, 0.7248, 0.7418,  ..., 0.3501, 0.3707, 0.8158],\n",
              "          [0.6455, 0.6923, 0.7242,  ..., 0.4144, 0.4178, 0.8015]],\n",
              " \n",
              "         [[0.5457, 0.5861, 0.5963,  ..., 0.9360, 0.8880, 0.9719],\n",
              "          [0.5593, 0.5917, 0.6009,  ..., 0.9692, 0.9330, 0.9784],\n",
              "          [0.5715, 0.5879, 0.5945,  ..., 0.9843, 0.9581, 0.9829],\n",
              "          ...,\n",
              "          [0.9289, 0.9695, 0.9687,  ..., 0.9176, 0.8556, 0.9530],\n",
              "          [0.9192, 0.9555, 0.9616,  ..., 0.8123, 0.7230, 0.9299],\n",
              "          [0.8441, 0.8786, 0.8999,  ..., 0.9201, 0.8169, 0.9404]]]),\n",
              " tensor(119.))"
            ]
          },
          "metadata": {},
          "execution_count": 98
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#print a random image from the dataset\n",
        "import random\n",
        "i = random.randint(0, 132)\n",
        "# x = dataset[i][\"image\"]\n",
        "# y = dataset[i][\"label\"]\n",
        "# size = dataset[i][\"image\"].shape\n",
        "img, label = dataset[i]\n",
        "size = img.shape\n",
        "print(f\"INTENSITY: {label} KNOTS\")\n",
        "print(f\"SIZE: {size}\\n\")\n",
        "plt.imshow(img.permute(1, 2, 0))\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 321
        },
        "id": "g6WTONp_nZ0m",
        "outputId": "035054f9-2c47-4f3e-c7db-fb3f51094c0b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "INTENSITY: 40.0 KNOTS\n",
            "SIZE: torch.Size([3, 250, 250])\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "for i in range(132):\n",
        "  x, y = dataset[i]\n",
        "  # x = dataset[i][\"image\"]\n",
        "  print(x.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kVgAvXfNwAwo",
        "outputId": "cf8ece68-f9ea-41a1-b0a3-aa989286891e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n",
            "torch.Size([3, 250, 250])\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# RESIZE TO SAME\n",
        "# DONE :D"
      ],
      "metadata": {
        "id": "3AF6Y6f20wUf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "class Model(nn.Module):\n",
        "  def __init__(self):\n",
        "    super().__init__()\n",
        "    self.model = nn.Sequential(\n",
        "        nn.Conv2d(3, 256, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(256),\n",
        "        nn.ReLU(),\n",
        "        nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(256),\n",
        "        nn.ReLU(),\n",
        "        nn.MaxPool2d(2),\n",
        "\n",
        "        nn.Conv2d(256, 128, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(128),\n",
        "        nn.ReLU(),\n",
        "        nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(128),\n",
        "        nn.ReLU(),\n",
        "        nn.MaxPool2d(2),\n",
        "\n",
        "        nn.Conv2d(128, 64, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(64),\n",
        "        nn.ReLU(),\n",
        "        nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(64),\n",
        "        nn.ReLU(),\n",
        "        nn.MaxPool2d(2),\n",
        "\n",
        "        nn.Conv2d(64, 32, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(32),\n",
        "        nn.ReLU(),\n",
        "        nn.Conv2d(32, 32, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(32),\n",
        "        nn.ReLU(),\n",
        "        nn.MaxPool2d(2),\n",
        "\n",
        "        nn.Conv2d(32, 16, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(16),\n",
        "        nn.ReLU(),\n",
        "        nn.Conv2d(16, 16, kernel_size=3, stride=1, padding=1),\n",
        "        nn.BatchNorm2d(16),\n",
        "        nn.ReLU(),\n",
        "        nn.MaxPool2d(2),\n",
        "\n",
        "        nn.Flatten(),\n",
        "        nn.Linear(784, 1),\n",
        "    )\n",
        "  def forward(self, x):\n",
        "    return self.model(x)"
      ],
      "metadata": {
        "id": "T2Qg8QMgg9vg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
        "device"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LZOICNKqEpJh",
        "outputId": "f856bc8d-8a9a-41e6-91c1-270f95db8132"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "device(type='cuda', index=0)"
            ]
          },
          "metadata": {},
          "execution_count": 127
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model = Model().to(device)\n",
        "summary(model, (3, 250, 250))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "y9t8UbWHBUwv",
        "outputId": "fe422174-a581-4155-da88-0837e0442078"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "----------------------------------------------------------------\n",
            "        Layer (type)               Output Shape         Param #\n",
            "================================================================\n",
            "            Conv2d-1        [-1, 256, 250, 250]           7,168\n",
            "       BatchNorm2d-2        [-1, 256, 250, 250]             512\n",
            "              ReLU-3        [-1, 256, 250, 250]               0\n",
            "            Conv2d-4        [-1, 256, 250, 250]         590,080\n",
            "       BatchNorm2d-5        [-1, 256, 250, 250]             512\n",
            "              ReLU-6        [-1, 256, 250, 250]               0\n",
            "         MaxPool2d-7        [-1, 256, 125, 125]               0\n",
            "            Conv2d-8        [-1, 128, 125, 125]         295,040\n",
            "       BatchNorm2d-9        [-1, 128, 125, 125]             256\n",
            "             ReLU-10        [-1, 128, 125, 125]               0\n",
            "           Conv2d-11        [-1, 128, 125, 125]         147,584\n",
            "      BatchNorm2d-12        [-1, 128, 125, 125]             256\n",
            "             ReLU-13        [-1, 128, 125, 125]               0\n",
            "        MaxPool2d-14          [-1, 128, 62, 62]               0\n",
            "           Conv2d-15           [-1, 64, 62, 62]          73,792\n",
            "      BatchNorm2d-16           [-1, 64, 62, 62]             128\n",
            "             ReLU-17           [-1, 64, 62, 62]               0\n",
            "           Conv2d-18           [-1, 64, 62, 62]          36,928\n",
            "      BatchNorm2d-19           [-1, 64, 62, 62]             128\n",
            "             ReLU-20           [-1, 64, 62, 62]               0\n",
            "        MaxPool2d-21           [-1, 64, 31, 31]               0\n",
            "           Conv2d-22           [-1, 32, 31, 31]          18,464\n",
            "      BatchNorm2d-23           [-1, 32, 31, 31]              64\n",
            "             ReLU-24           [-1, 32, 31, 31]               0\n",
            "           Conv2d-25           [-1, 32, 31, 31]           9,248\n",
            "      BatchNorm2d-26           [-1, 32, 31, 31]              64\n",
            "             ReLU-27           [-1, 32, 31, 31]               0\n",
            "        MaxPool2d-28           [-1, 32, 15, 15]               0\n",
            "           Conv2d-29           [-1, 16, 15, 15]           4,624\n",
            "      BatchNorm2d-30           [-1, 16, 15, 15]              32\n",
            "             ReLU-31           [-1, 16, 15, 15]               0\n",
            "           Conv2d-32           [-1, 16, 15, 15]           2,320\n",
            "      BatchNorm2d-33           [-1, 16, 15, 15]              32\n",
            "             ReLU-34           [-1, 16, 15, 15]               0\n",
            "        MaxPool2d-35             [-1, 16, 7, 7]               0\n",
            "          Flatten-36                  [-1, 784]               0\n",
            "           Linear-37                    [-1, 1]             785\n",
            "================================================================\n",
            "Total params: 1,188,017\n",
            "Trainable params: 1,188,017\n",
            "Non-trainable params: 0\n",
            "----------------------------------------------------------------\n",
            "Input size (MB): 0.72\n",
            "Forward/backward pass size (MB): 871.62\n",
            "Params size (MB): 4.53\n",
            "Estimated Total Size (MB): 876.86\n",
            "----------------------------------------------------------------\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "loss_per_iteration = []\n",
        "def train_batch(epochs, model, criterion, optimizer, train_loader):\n",
        "  total = 0\n",
        "  correct = 0 \n",
        "  for i in range(epochs):\n",
        "    train_loss = 0.0\n",
        "    for inputs, labels in train_loader:\n",
        "      inputs, labels = inputs.to(device), labels.to(device)\n",
        "      outputs = model(inputs)\n",
        "      labels = torch.unsqueeze(labels, 1)\n",
        "      loss = criterion(outputs, labels)\n",
        "      optimizer.zero_grad()\n",
        "      loss.backward()\n",
        "      optimizer.step()\n",
        "      train_loss = train_loss + loss.item()\n",
        "\n",
        "    print(f\"Epoch: {i}/{epochs} Loss: {train_loss/len(train_loader):.5f} \")\n",
        "    loss_per_iteration.append(train_loss/len(train_loader))"
      ],
      "metadata": {
        "id": "LdtlXb-CD-S-"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "gpu_info = !nvidia-smi\n",
        "gpu_info = '\\n'.join(gpu_info)\n",
        "if gpu_info.find('failed') >= 0:\n",
        "  print('Not connected to a GPU')\n",
        "else:\n",
        "  print(gpu_info)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ap5p8V5zW-yv",
        "outputId": "54e55f6f-2431-4db5-8f55-83c5e92d0cde"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Tue Mar 15 09:41:23 2022       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla P100-PCIE...  Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   47C    P0    34W / 250W |   7809MiB / 16280MiB |      0%      Default |\n",
            "|                               |                      |                  N/A |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "+-----------------------------------------------------------------------------+\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model = Model().to(device)\n",
        "criterion = nn.MSELoss()\n",
        "optimizer = torch.optim.Adam(model.parameters(), lr =0.001)\n",
        "\n",
        "train_batch(epochs=35,\n",
        "            model=model,\n",
        "            criterion=criterion,\n",
        "            optimizer=optimizer,\n",
        "            train_loader = data_loader)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6qt-U6zLLLdH",
        "outputId": "7efd778e-3d00-44a2-891e-ee3a003061dd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch: 0/40 Loss: 2411.31552 \n",
            "Epoch: 1/40 Loss: 915.67965 \n",
            "Epoch: 2/40 Loss: 497.40488 \n",
            "Epoch: 3/40 Loss: 453.76269 \n",
            "Epoch: 4/40 Loss: 452.09357 \n",
            "Epoch: 5/40 Loss: 491.28315 \n",
            "Epoch: 6/40 Loss: 403.75021 \n",
            "Epoch: 7/40 Loss: 422.87397 \n",
            "Epoch: 8/40 Loss: 406.61560 \n",
            "Epoch: 9/40 Loss: 340.29401 \n",
            "Epoch: 10/40 Loss: 399.35788 \n",
            "Epoch: 11/40 Loss: 350.00114 \n",
            "Epoch: 12/40 Loss: 324.78222 \n",
            "Epoch: 13/40 Loss: 290.93693 \n",
            "Epoch: 14/40 Loss: 317.79394 \n",
            "Epoch: 15/40 Loss: 295.02648 \n",
            "Epoch: 16/40 Loss: 288.30678 \n",
            "Epoch: 17/40 Loss: 272.29258 \n",
            "Epoch: 18/40 Loss: 255.22025 \n",
            "Epoch: 19/40 Loss: 231.20786 \n",
            "Epoch: 20/40 Loss: 233.57762 \n",
            "Epoch: 21/40 Loss: 240.36691 \n",
            "Epoch: 22/40 Loss: 225.28644 \n",
            "Epoch: 23/40 Loss: 215.36949 \n",
            "Epoch: 24/40 Loss: 202.09612 \n",
            "Epoch: 25/40 Loss: 187.29650 \n",
            "Epoch: 26/40 Loss: 188.39581 \n",
            "Epoch: 27/40 Loss: 156.10751 \n",
            "Epoch: 28/40 Loss: 142.67887 \n",
            "Epoch: 29/40 Loss: 164.61677 \n",
            "Epoch: 30/40 Loss: 169.65871 \n",
            "Epoch: 31/40 Loss: 175.85457 \n",
            "Epoch: 32/40 Loss: 125.78276 \n",
            "Epoch: 33/40 Loss: 152.69629 \n",
            "Epoch: 34/40 Loss: 165.91800 \n",
            "Epoch: 35/40 Loss: 115.17895 \n",
            "Epoch: 36/40 Loss: 140.73650 \n",
            "Epoch: 37/40 Loss: 98.74439 \n",
            "Epoch: 38/40 Loss: 112.15816 \n",
            "Epoch: 39/40 Loss: 92.24528 \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.eval()"
      ],
      "metadata": {
        "id": "uoCL0OdAAZ66"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "img = cv2.imread('/content/94.jpg')\n",
        "img = np.array(img)\n",
        "totensor = transforms.ToTensor()\n",
        "img = totensor(img)\n",
        "resize = transforms.Resize(size=(248, 248))\n",
        "img = resize(img)\n",
        "img = torch.unsqueeze(img, 0)\n",
        "img = img.to(device)\n",
        "model(img)"
      ],
      "metadata": {
        "id": "e1FftiTTb93b"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#96-112knots"
      ],
      "metadata": {
        "id": "gnK2zHC3fZeG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "img = cv2.imread('/content/43(2).jpg')\n",
        "img = np.array(img)\n",
        "totensor = transforms.ToTensor()\n",
        "img = totensor(img)\n",
        "resize = transforms.Resize(size=(248, 248))\n",
        "img = resize(img)\n",
        "img = torch.unsqueeze(img, 0)\n",
        "img = img.to(device)\n",
        "model(img)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "oYtRqg7yEFBW",
        "outputId": "e9e6a598-dfd5-4523-d17d-72bb232c638d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[56.1818]], device='cuda:0', grad_fn=<AddmmBackward0>)"
            ]
          },
          "metadata": {},
          "execution_count": 133
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from pip._internal.utils.misc import get_installed_distributions\n",
        "import sys\n",
        "#import numpy as np # imported to test whether numpy shows up, which it does!\n",
        "\n",
        "def get_imported_packages():\n",
        "    p = get_installed_distributions()\n",
        "    p = {package.key:package.version for package in p}\n",
        "\n",
        "    imported_modules = set(sys.modules.keys())\n",
        "    \n",
        "    imported_modules.remove('pip')\n",
        "\n",
        "    modules = [(m, p[m]) for m in imported_modules if p.get(m, False)]\n",
        "\n",
        "    return modules\n",
        "\n",
        "\n",
        "def generate_requirements(filepath:str, modules):\n",
        "    with open(filepath, 'w') as f:\n",
        "        for module, version in modules:\n",
        "            f.write(f\"{module}=={version}\")\n",
        "\n",
        "\n",
        "generate_requirements('requirements.txt', get_imported_packages())"
      ],
      "metadata": {
        "id": "wtdIKlL_XtSQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "saved_path = './saved_modelcyclonr'\n",
        "torch.save(model.state_dict(), saved_path)"
      ],
      "metadata": {
        "id": "8C-6sMAlfYru"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# torch.save(model.state_dict,'cyclonemodel2.h5')"
      ],
      "metadata": {
        "id": "j9nAGdnx9bAu"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# torch.save(model.state_dict,'cyclonemodel2.pth')"
      ],
      "metadata": {
        "id": "tgBvMdfaBlep"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model= Model()\n",
        "model.load_state_dict(torch.load('/content/saved_modelcyclone', map_location=torch.device('cpu')))\n",
        "model.eval()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tNTMIkViO-_k",
        "outputId": "165319ce-d8b9-4e6e-9d0f-1bad2449e3ea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Model(\n",
              "  (model): Sequential(\n",
              "    (0): Conv2d(3, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (2): ReLU()\n",
              "    (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (5): ReLU()\n",
              "    (6): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
              "    (7): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (9): ReLU()\n",
              "    (10): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (11): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (12): ReLU()\n",
              "    (13): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
              "    (14): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (15): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (16): ReLU()\n",
              "    (17): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (18): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (19): ReLU()\n",
              "    (20): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
              "    (21): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (22): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (23): ReLU()\n",
              "    (24): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (25): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (26): ReLU()\n",
              "    (27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
              "    (28): Conv2d(32, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (29): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (30): ReLU()\n",
              "    (31): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
              "    (32): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "    (33): ReLU()\n",
              "    (34): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
              "    (35): Flatten(start_dim=1, end_dim=-1)\n",
              "    (36): Linear(in_features=784, out_features=1, bias=True)\n",
              "  )\n",
              ")"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "path = '/content/30.jpg'\n",
        "img = cv2.imread(path)\n",
        "img = np.array(img)\n",
        "totensor = transforms.ToTensor()\n",
        "img = totensor(img)\n",
        "resize = transforms.Resize(size=(250, 250))\n",
        "img = resize(img)\n",
        "img = torch.unsqueeze(img, 0)\n",
        "# img = img.to(device)\n",
        "model(img)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PTyKnbq3n2J8",
        "outputId": "cb344d72-da67-4143-c46b-d916f0d57b59"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[41.0617]], grad_fn=<AddmmBackward0>)"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "path = '/content/94.jpg'\n",
        "img = cv2.imread(path)\n",
        "img = np.array(img)\n",
        "totensor = transforms.ToTensor()\n",
        "img = totensor(img)\n",
        "resize = transforms.Resize(size=(250, 250))\n",
        "img = resize(img)\n",
        "img = torch.unsqueeze(img, 0)\n",
        "# img = img.to(device)\n",
        "model(img)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ai-nQFcdRI0R",
        "outputId": "ad1aca34-3e47-4573-9075-c69fd77051f6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[81.0453]], grad_fn=<AddmmBackward0>)"
            ]
          },
          "metadata": {},
          "execution_count": 161
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import files\n",
        "files.download('saved_modelcyclone')"
      ],
      "metadata": {
        "id": "2VqiO1ee4gEe"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}