{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 34,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "58JEVtlvy2Ij",
        "outputId": "9485e805-6bfb-4234-f0d2-49d2d82e611c"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-a46cb6bf-eb81-4a53-8766-4d57f0f917bf\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-a46cb6bf-eb81-4a53-8766-4d57f0f917bf\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving DBMNK.zip to DBMNK (4).zip\n"
          ]
        }
      ],
      "source": [
        "from google.colab import files\n",
        "uploaded = files.upload()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import zipfile\n",
        "import os\n",
        "\n",
        "# Unzip the dataset\n",
        "with zipfile.ZipFile('DBMNK (4).zip', 'r') as zip_ref:\n",
        "    zip_ref.extractall('DBMNK')\n",
        "\n",
        "# Verify the dataset structure\n",
        "os.listdir('DBMNK')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X1fO2-rVKArA",
        "outputId": "6d7d6cb2-9afd-43c5-8158-932f5ff0637a"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['Monkeypox Skin Image Dataset']"
            ]
          },
          "metadata": {},
          "execution_count": 42
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "os.listdir('DBMNK/Monkeypox Skin Image Dataset/Monkeypox')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SV2q2mNjOelx",
        "outputId": "86d17b0f-1bd7-47e3-f403-703c173506cf"
      },
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['monkeypox24.png',\n",
              " 'monkeypox267.png',\n",
              " 'monkeypox278.png',\n",
              " 'monkeypox17.png',\n",
              " 'monkeypox256.png',\n",
              " 'monkeypox117.png',\n",
              " 'monkeypox258.png',\n",
              " 'monkeypox229.png',\n",
              " 'monkeypox191.png',\n",
              " 'monkeypox66.png',\n",
              " 'monkeypox177.png',\n",
              " 'monkeypox206.png',\n",
              " 'monkeypox108.png',\n",
              " 'monkeypox101.png',\n",
              " 'monkeypox97.png',\n",
              " 'monkeypox203.png',\n",
              " 'monkeypox238.png',\n",
              " 'monkeypox259.png',\n",
              " 'monkeypox186.png',\n",
              " 'monkeypox47.png',\n",
              " 'monkeypox41.png',\n",
              " 'monkeypox50.png',\n",
              " 'monkeypox4.png',\n",
              " 'monkeypox85.png',\n",
              " 'monkeypox12.png',\n",
              " 'monkeypox9.png',\n",
              " 'monkeypox122.png',\n",
              " 'monkeypox109.png',\n",
              " 'monkeypox128.png',\n",
              " 'monkeypox201.png',\n",
              " 'monkeypox118.png',\n",
              " 'monkeypox131.png',\n",
              " 'monkeypox249.png',\n",
              " 'monkeypox38.png',\n",
              " 'monkeypox157.png',\n",
              " 'monkeypox192.png',\n",
              " 'monkeypox220.png',\n",
              " 'monkeypox106.png',\n",
              " 'monkeypox245.png',\n",
              " 'monkeypox193.png',\n",
              " 'monkeypox269.png',\n",
              " 'monkeypox144.png',\n",
              " 'monkeypox170.png',\n",
              " 'monkeypox149.png',\n",
              " 'monkeypox260.png',\n",
              " 'monkeypox130.png',\n",
              " 'monkeypox173.png',\n",
              " 'monkeypox114.png',\n",
              " 'monkeypox40.png',\n",
              " 'monkeypox235.png',\n",
              " 'monkeypox223.png',\n",
              " 'monkeypox18.png',\n",
              " 'monkeypox198.png',\n",
              " 'monkeypox225.png',\n",
              " 'monkeypox160.png',\n",
              " 'monkeypox82.png',\n",
              " 'monkeypox107.png',\n",
              " 'monkeypox55.png',\n",
              " 'monkeypox121.png',\n",
              " 'monkeypox234.png',\n",
              " 'monkeypox158.png',\n",
              " 'monkeypox262.png',\n",
              " 'monkeypox255.png',\n",
              " 'monkeypox213.png',\n",
              " 'monkeypox217.png',\n",
              " 'monkeypox56.png',\n",
              " 'monkeypox70.png',\n",
              " 'monkeypox167.png',\n",
              " 'monkeypox176.png',\n",
              " 'monkeypox8.png',\n",
              " 'monkeypox115.png',\n",
              " 'monkeypox84.png',\n",
              " 'monkeypox153.png',\n",
              " 'monkeypox86.png',\n",
              " 'monkeypox214.png',\n",
              " 'monkeypox93.png',\n",
              " 'monkeypox211.png',\n",
              " 'monkeypox49.png',\n",
              " 'monkeypox127.png',\n",
              " 'monkeypox52.png',\n",
              " 'monkeypox184.png',\n",
              " 'monkeypox57.png',\n",
              " 'monkeypox46.png',\n",
              " 'monkeypox36.png',\n",
              " 'monkeypox251.png',\n",
              " 'monkeypox58.png',\n",
              " 'monkeypox67.png',\n",
              " 'monkeypox159.png',\n",
              " 'monkeypox89.png',\n",
              " 'monkeypox180.png',\n",
              " 'monkeypox241.png',\n",
              " 'monkeypox135.png',\n",
              " 'monkeypox15.png',\n",
              " 'monkeypox75.png',\n",
              " 'monkeypox161.png',\n",
              " 'monkeypox145.png',\n",
              " 'monkeypox257.png',\n",
              " 'monkeypox194.png',\n",
              " 'monkeypox19.png',\n",
              " 'monkeypox237.png',\n",
              " 'monkeypox272.png',\n",
              " 'monkeypox142.png',\n",
              " 'monkeypox23.png',\n",
              " 'monkeypox91.png',\n",
              " 'monkeypox62.png',\n",
              " 'monkeypox80.png',\n",
              " 'monkeypox275.png',\n",
              " 'monkeypox202.png',\n",
              " 'monkeypox27.png',\n",
              " 'monkeypox178.png',\n",
              " 'monkeypox164.png',\n",
              " 'monkeypox231.png',\n",
              " 'monkeypox112.png',\n",
              " 'monkeypox175.png',\n",
              " 'monkeypox239.png',\n",
              " 'monkeypox232.png',\n",
              " 'monkeypox248.png',\n",
              " 'monkeypox252.png',\n",
              " 'monkeypox187.png',\n",
              " 'monkeypox274.png',\n",
              " 'monkeypox228.png',\n",
              " 'monkeypox53.png',\n",
              " 'monkeypox171.png',\n",
              " 'monkeypox33.png',\n",
              " 'monkeypox265.png',\n",
              " 'monkeypox247.png',\n",
              " 'monkeypox32.png',\n",
              " 'monkeypox54.png',\n",
              " 'monkeypox156.png',\n",
              " 'monkeypox246.png',\n",
              " 'monkeypox59.png',\n",
              " 'monkeypox165.png',\n",
              " 'monkeypox221.png',\n",
              " 'monkeypox169.png',\n",
              " 'monkeypox111.png',\n",
              " 'monkeypox87.png',\n",
              " 'monkeypox28.png',\n",
              " 'monkeypox95.png',\n",
              " 'monkeypox226.png',\n",
              " 'monkeypox16.png',\n",
              " 'monkeypox125.png',\n",
              " 'monkeypox92.png',\n",
              " 'monkeypox270.png',\n",
              " 'monkeypox104.png',\n",
              " 'monkeypox37.png',\n",
              " 'monkeypox219.png',\n",
              " 'monkeypox133.png',\n",
              " 'monkeypox227.png',\n",
              " 'monkeypox148.png',\n",
              " 'monkeypox182.png',\n",
              " 'monkeypox132.png',\n",
              " 'monkeypox2.png',\n",
              " 'monkeypox126.png',\n",
              " 'monkeypox141.png',\n",
              " 'monkeypox94.png',\n",
              " 'monkeypox81.png',\n",
              " 'monkeypox199.png',\n",
              " 'monkeypox83.png',\n",
              " 'monkeypox155.png',\n",
              " 'monkeypox271.png',\n",
              " 'monkeypox65.png',\n",
              " 'monkeypox26.png',\n",
              " 'monkeypox222.png',\n",
              " 'monkeypox172.png',\n",
              " 'monkeypox110.png',\n",
              " 'monkeypox63.png',\n",
              " 'monkeypox266.png',\n",
              " 'monkeypox88.png',\n",
              " 'monkeypox273.png',\n",
              " 'monkeypox168.png',\n",
              " 'monkeypox188.png',\n",
              " 'monkeypox79.png',\n",
              " 'monkeypox207.png',\n",
              " 'monkeypox154.png',\n",
              " 'monkeypox45.png',\n",
              " 'monkeypox14.png',\n",
              " 'monkeypox174.png',\n",
              " 'monkeypox123.png',\n",
              " 'monkeypox116.png',\n",
              " 'monkeypox20.png',\n",
              " 'monkeypox210.png',\n",
              " 'monkeypox137.png',\n",
              " 'monkeypox120.png',\n",
              " 'monkeypox230.png',\n",
              " 'monkeypox179.png',\n",
              " 'monkeypox29.png',\n",
              " 'monkeypox64.png',\n",
              " 'monkeypox276.png',\n",
              " 'monkeypox261.png',\n",
              " 'monkeypox102.png',\n",
              " 'monkeypox254.png',\n",
              " 'monkeypox129.png',\n",
              " 'monkeypox21.png',\n",
              " 'monkeypox195.png',\n",
              " 'monkeypox74.png',\n",
              " 'monkeypox263.png',\n",
              " 'monkeypox1.png',\n",
              " 'monkeypox216.png',\n",
              " 'monkeypox31.png',\n",
              " 'monkeypox253.png',\n",
              " 'monkeypox242.png',\n",
              " 'monkeypox212.png',\n",
              " 'monkeypox152.png',\n",
              " 'monkeypox181.png',\n",
              " 'monkeypox68.png',\n",
              " 'monkeypox76.png',\n",
              " 'monkeypox215.png',\n",
              " 'monkeypox250.png',\n",
              " 'monkeypox13.png',\n",
              " 'monkeypox98.png',\n",
              " 'monkeypox200.png',\n",
              " 'monkeypox197.png',\n",
              " 'monkeypox204.png',\n",
              " 'monkeypox147.png',\n",
              " 'monkeypox35.png',\n",
              " 'monkeypox138.png',\n",
              " 'monkeypox150.png',\n",
              " 'monkeypox279.png',\n",
              " 'monkeypox5.png',\n",
              " 'monkeypox11.png',\n",
              " 'monkeypox105.png',\n",
              " 'monkeypox25.png',\n",
              " 'monkeypox163.png',\n",
              " 'monkeypox196.png',\n",
              " 'monkeypox162.png',\n",
              " 'monkeypox208.png',\n",
              " 'monkeypox143.png',\n",
              " 'monkeypox224.png',\n",
              " 'monkeypox60.png',\n",
              " 'monkeypox96.png',\n",
              " 'monkeypox140.png',\n",
              " 'monkeypox119.png',\n",
              " 'monkeypox78.png',\n",
              " 'monkeypox10.png',\n",
              " 'monkeypox268.png',\n",
              " 'monkeypox39.png',\n",
              " 'monkeypox90.png',\n",
              " 'monkeypox6.png',\n",
              " 'monkeypox205.png',\n",
              " 'monkeypox146.png',\n",
              " 'monkeypox134.png',\n",
              " 'monkeypox30.png',\n",
              " 'monkeypox22.png',\n",
              " 'monkeypox124.png',\n",
              " 'monkeypox113.png',\n",
              " 'monkeypox99.png',\n",
              " 'monkeypox166.png',\n",
              " 'monkeypox185.png',\n",
              " 'monkeypox139.png',\n",
              " 'monkeypox100.png',\n",
              " 'monkeypox71.png',\n",
              " 'monkeypox244.png',\n",
              " 'monkeypox73.png',\n",
              " 'monkeypox43.png',\n",
              " 'monkeypox77.png',\n",
              " 'monkeypox103.png',\n",
              " 'monkeypox236.png',\n",
              " 'monkeypox48.png',\n",
              " 'monkeypox189.png',\n",
              " 'monkeypox3.png',\n",
              " 'monkeypox72.png',\n",
              " 'monkeypox34.png',\n",
              " 'monkeypox190.png',\n",
              " 'monkeypox233.png',\n",
              " 'monkeypox240.png',\n",
              " 'monkeypox209.png',\n",
              " 'monkeypox277.png',\n",
              " 'monkeypox136.png',\n",
              " 'monkeypox42.png',\n",
              " 'monkeypox44.png',\n",
              " 'monkeypox7.png',\n",
              " 'monkeypox243.png',\n",
              " 'monkeypox69.png',\n",
              " 'monkeypox61.png',\n",
              " 'monkeypox51.png',\n",
              " 'monkeypox218.png',\n",
              " 'monkeypox264.png',\n",
              " 'monkeypox151.png',\n",
              " 'monkeypox183.png']"
            ]
          },
          "metadata": {},
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "qL0RXg6uRBQc"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install tensorflow\n",
        "!pip install matplotlib\n",
        "!pip install seaborn\n",
        "!pip install scikit-learn"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JXe6qbD8KFSL",
        "outputId": "890e09fe-56fa-47cc-8ff0-c81f457277fc"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: tensorflow in /usr/local/lib/python3.11/dist-packages (2.18.0)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=24.3.25 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (25.2.10)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (0.6.0)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (18.1.1)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (3.4.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from tensorflow) (24.2)\n",
            "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.3 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (4.25.6)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (2.32.3)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.11/dist-packages (from tensorflow) (75.1.0)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (1.17.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (2.5.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (4.12.2)\n",
            "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (1.17.2)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (1.70.0)\n",
            "Requirement already satisfied: tensorboard<2.19,>=2.18 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (2.18.0)\n",
            "Requirement already satisfied: keras>=3.5.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (3.8.0)\n",
            "Requirement already satisfied: numpy<2.1.0,>=1.26.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (1.26.4)\n",
            "Requirement already satisfied: h5py>=3.11.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (3.12.1)\n",
            "Requirement already satisfied: ml-dtypes<0.5.0,>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (0.4.1)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.11/dist-packages (from tensorflow) (0.37.1)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.11/dist-packages (from astunparse>=1.6.0->tensorflow) (0.45.1)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.11/dist-packages (from keras>=3.5.0->tensorflow) (13.9.4)\n",
            "Requirement already satisfied: namex in /usr/local/lib/python3.11/dist-packages (from keras>=3.5.0->tensorflow) (0.0.8)\n",
            "Requirement already satisfied: optree in /usr/local/lib/python3.11/dist-packages (from keras>=3.5.0->tensorflow) (0.14.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.4.1)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests<3,>=2.21.0->tensorflow) (2.3.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests<3,>=2.21.0->tensorflow) (2025.1.31)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.11/dist-packages (from tensorboard<2.19,>=2.18->tensorflow) (3.7)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from tensorboard<2.19,>=2.18->tensorflow) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from tensorboard<2.19,>=2.18->tensorflow) (3.1.3)\n",
            "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.11/dist-packages (from werkzeug>=1.0.1->tensorboard<2.19,>=2.18->tensorflow) (3.0.2)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich->keras>=3.5.0->tensorflow) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich->keras>=3.5.0->tensorflow) (2.18.0)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich->keras>=3.5.0->tensorflow) (0.1.2)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (3.10.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (1.3.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (4.56.0)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (1.4.8)\n",
            "Requirement already satisfied: numpy>=1.23 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (1.26.4)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (24.2)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (11.1.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (3.2.1)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib) (2.8.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib) (1.17.0)\n",
            "Requirement already satisfied: seaborn in /usr/local/lib/python3.11/dist-packages (0.13.2)\n",
            "Requirement already satisfied: numpy!=1.24.0,>=1.20 in /usr/local/lib/python3.11/dist-packages (from seaborn) (1.26.4)\n",
            "Requirement already satisfied: pandas>=1.2 in /usr/local/lib/python3.11/dist-packages (from seaborn) (2.2.2)\n",
            "Requirement already satisfied: matplotlib!=3.6.1,>=3.4 in /usr/local/lib/python3.11/dist-packages (from seaborn) (3.10.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.3.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (4.56.0)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.4.8)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (24.2)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (11.1.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (3.2.1)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2->seaborn) (2025.1)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2->seaborn) (2025.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib!=3.6.1,>=3.4->seaborn) (1.17.0)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (1.6.1)\n",
            "Requirement already satisfied: numpy>=1.19.5 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.26.4)\n",
            "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.13.1)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.4.2)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (3.5.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Dense, Flatten, Dropout, GlobalAveragePooling2D\n",
        "from tensorflow.keras.applications import ResNet50, EfficientNetB0\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score, classification_report\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "from sklearn.model_selection import train_test_split\n",
        "import os\n",
        "import shutil"
      ],
      "metadata": {
        "id": "W9Ht5ycrKJLD"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "original_dataset_dir = 'DBMNK/Monkeypox Skin Image Dataset'  # Path to the dataset\n",
        "base_dir = 'dataset'  # Where you want to save new directories\n",
        "train_dir = os.path.join(base_dir, 'train')\n",
        "validation_dir = os.path.join(base_dir, 'validation')\n",
        "test_dir = os.path.join(base_dir, 'test')\n",
        "\n",
        "# Create directories if they do not exist\n",
        "for dir_path in [train_dir, validation_dir, test_dir]:\n",
        "    os.makedirs(dir_path, exist_ok=True)"
      ],
      "metadata": {
        "id": "UFRIvktSKQ2U"
      },
      "execution_count": 47,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Split ratios\n",
        "train_ratio = 0.7\n",
        "validation_ratio = 0.1\n",
        "test_ratio = 0.2\n",
        "\n",
        "# Function to split and copy files\n",
        "def split_and_copy_files(class_dir, dest_base_dir):\n",
        "    # List all files in the class directory\n",
        "    all_images = [os.path.join(class_dir, f) for f in os.listdir(class_dir) if os.path.isfile(os.path.join(class_dir, f))]\n",
        "\n",
        "    # Debug: Print the number of images found\n",
        "    print(f\"Found {len(all_images)} images in {class_dir}\")\n",
        "\n",
        "    # If no images are found, skip this class\n",
        "    if len(all_images) == 0:\n",
        "        print(f\"No images found in {class_dir}. Skipping.\")\n",
        "        return\n",
        "\n",
        "    # Split the images into train, validation, and test sets\n",
        "    train_images, temp_images = train_test_split(all_images, test_size=(1 - train_ratio), random_state=42)\n",
        "    validation_images, test_images = train_test_split(temp_images, test_size=test_ratio/(validation_ratio + test_ratio), random_state=42)\n",
        "\n",
        "    # Copy images to their respective directories\n",
        "    for images, folder_name in zip([train_images, validation_images, test_images], ['train', 'validation', 'test']):\n",
        "        dest_dir = os.path.join(dest_base_dir, folder_name, os.path.basename(class_dir))\n",
        "        os.makedirs(dest_dir, exist_ok=True)\n",
        "        for file in images:\n",
        "            shutil.copy(file, dest_dir)\n",
        "\n",
        "# Iterate over each class directory and split the files\n",
        "for class_dir in os.listdir(original_dataset_dir):\n",
        "    full_class_dir = os.path.join(original_dataset_dir, class_dir)\n",
        "    if os.path.isdir(full_class_dir):\n",
        "        split_and_copy_files(full_class_dir, base_dir)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LTSKgikKKU9F",
        "outputId": "84a92c76-d389-4b45-e8e4-a94dfd7c9b3d"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 91 images in DBMNK/Monkeypox Skin Image Dataset/Measles\n",
            "Found 279 images in DBMNK/Monkeypox Skin Image Dataset/Monkeypox\n",
            "Found 107 images in DBMNK/Monkeypox Skin Image Dataset/Chickenpox\n",
            "Found 293 images in DBMNK/Monkeypox Skin Image Dataset/Normal\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def create_data_generators(train_dir, val_dir, test_dir, img_size=(240, 240), batch_size=32):\n",
        "    # Data augmentation for training dataset\n",
        "    train_datagen = ImageDataGenerator(\n",
        "        rescale=1./255,\n",
        "        rotation_range=360,\n",
        "        horizontal_flip=True,\n",
        "        vertical_flip=True,\n",
        "        brightness_range=(0.75, 1.25)\n",
        "    )\n",
        "\n",
        "    # Only rescale for validation and testing\n",
        "    val_test_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "    # Generate augmented training images\n",
        "    train_generator = train_datagen.flow_from_directory(\n",
        "        train_dir,\n",
        "        target_size=img_size,\n",
        "        batch_size=batch_size,\n",
        "        class_mode='categorical',\n",
        "        shuffle=True\n",
        "    )\n",
        "\n",
        "    # Generate validation images\n",
        "    val_generator = val_test_datagen.flow_from_directory(\n",
        "        val_dir,\n",
        "        target_size=img_size,\n",
        "        batch_size=batch_size,\n",
        "        class_mode='categorical',\n",
        "        shuffle=False\n",
        "    )\n",
        "\n",
        "    # Generate test images\n",
        "    test_generator = val_test_datagen.flow_from_directory(\n",
        "        test_dir,\n",
        "        target_size=img_size,\n",
        "        batch_size=batch_size,\n",
        "        class_mode='categorical',\n",
        "        shuffle=False\n",
        "    )\n",
        "\n",
        "    return train_generator, val_generator, test_generator\n",
        "\n",
        "# Create data generators\n",
        "train_gen, val_gen, test_gen = create_data_generators(train_dir, validation_dir, test_dir)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1TT41EUURnrM",
        "outputId": "b3d93aad-2b75-44f3-9014-02de503d1375"
      },
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 537 images belonging to 4 classes.\n",
            "Found 77 images belonging to 4 classes.\n",
            "Found 156 images belonging to 4 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def build_resnet50_model(input_shape, num_classes):\n",
        "    base_model = ResNet50(weights='imagenet', include_top=False, input_shape=input_shape)\n",
        "    base_model.trainable = False  # Freeze the base model\n",
        "\n",
        "    model = Sequential([\n",
        "        base_model,\n",
        "        GlobalAveragePooling2D(),\n",
        "        Dense(128, activation='relu'),\n",
        "        Dropout(0.5),\n",
        "        Dense(num_classes, activation='softmax')\n",
        "    ])\n",
        "\n",
        "    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "    return model\n",
        "\n",
        "# Get input shape and number of classes\n",
        "input_shape = (240, 240, 3)\n",
        "num_classes = len(train_gen.class_indices)\n",
        "\n",
        "# Build the model\n",
        "model_resnet50 = build_resnet50_model(input_shape, num_classes)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fc6UP2bRRyJR",
        "outputId": "495c330b-71b5-4193-accc-87670b5e0765"
      },
      "execution_count": 50,
      "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",
            "\u001b[1m94765736/94765736\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "history = model_resnet50.fit(train_gen, epochs=50, validation_data=val_gen)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4Z7VRw2eR5Ub",
        "outputId": "61cb39e8-8e6e-4029-8d99-c566ccd8c22f"
      },
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m173s\u001b[0m 10s/step - accuracy: 0.2716 - loss: 1.6186 - val_accuracy: 0.3766 - val_loss: 1.2712\n",
            "Epoch 2/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 8s/step - accuracy: 0.4431 - loss: 1.2525 - val_accuracy: 0.5065 - val_loss: 1.2617\n",
            "Epoch 3/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m145s\u001b[0m 9s/step - accuracy: 0.3663 - loss: 1.2865 - val_accuracy: 0.3766 - val_loss: 1.2520\n",
            "Epoch 4/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 8s/step - accuracy: 0.3543 - loss: 1.3146 - val_accuracy: 0.3766 - val_loss: 1.2552\n",
            "Epoch 5/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.3890 - loss: 1.2991 - val_accuracy: 0.3766 - val_loss: 1.2607\n",
            "Epoch 6/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.3753 - loss: 1.2579 - val_accuracy: 0.4286 - val_loss: 1.2549\n",
            "Epoch 7/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 8s/step - accuracy: 0.4112 - loss: 1.2946 - val_accuracy: 0.3766 - val_loss: 1.2465\n",
            "Epoch 8/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.4140 - loss: 1.2619 - val_accuracy: 0.3766 - val_loss: 1.2545\n",
            "Epoch 9/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.3572 - loss: 1.3141 - val_accuracy: 0.5584 - val_loss: 1.2415\n",
            "Epoch 10/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.4214 - loss: 1.2582 - val_accuracy: 0.5844 - val_loss: 1.2464\n",
            "Epoch 11/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 8s/step - accuracy: 0.3969 - loss: 1.2590 - val_accuracy: 0.3766 - val_loss: 1.2514\n",
            "Epoch 12/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 8s/step - accuracy: 0.4038 - loss: 1.2530 - val_accuracy: 0.5844 - val_loss: 1.2639\n",
            "Epoch 13/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4009 - loss: 1.2637 - val_accuracy: 0.3766 - val_loss: 1.2502\n",
            "Epoch 14/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 8s/step - accuracy: 0.3879 - loss: 1.2880 - val_accuracy: 0.3766 - val_loss: 1.2453\n",
            "Epoch 15/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m135s\u001b[0m 8s/step - accuracy: 0.4120 - loss: 1.2587 - val_accuracy: 0.3766 - val_loss: 1.2497\n",
            "Epoch 16/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 8s/step - accuracy: 0.4015 - loss: 1.3037 - val_accuracy: 0.4545 - val_loss: 1.2390\n",
            "Epoch 17/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 8s/step - accuracy: 0.4017 - loss: 1.2594 - val_accuracy: 0.3766 - val_loss: 1.2326\n",
            "Epoch 18/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.3951 - loss: 1.2796 - val_accuracy: 0.5974 - val_loss: 1.2340\n",
            "Epoch 19/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.4530 - loss: 1.2415 - val_accuracy: 0.6104 - val_loss: 1.2262\n",
            "Epoch 20/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4288 - loss: 1.2408 - val_accuracy: 0.4026 - val_loss: 1.2220\n",
            "Epoch 21/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 8s/step - accuracy: 0.4348 - loss: 1.2405 - val_accuracy: 0.5974 - val_loss: 1.2335\n",
            "Epoch 22/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4461 - loss: 1.2834 - val_accuracy: 0.3766 - val_loss: 1.2217\n",
            "Epoch 23/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 8s/step - accuracy: 0.4058 - loss: 1.2650 - val_accuracy: 0.5844 - val_loss: 1.2219\n",
            "Epoch 24/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.3855 - loss: 1.2460 - val_accuracy: 0.5714 - val_loss: 1.2229\n",
            "Epoch 25/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m147s\u001b[0m 8s/step - accuracy: 0.3950 - loss: 1.2655 - val_accuracy: 0.4286 - val_loss: 1.2253\n",
            "Epoch 26/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m135s\u001b[0m 8s/step - accuracy: 0.4157 - loss: 1.2641 - val_accuracy: 0.5974 - val_loss: 1.2158\n",
            "Epoch 27/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.4340 - loss: 1.2480 - val_accuracy: 0.5974 - val_loss: 1.2216\n",
            "Epoch 28/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m145s\u001b[0m 9s/step - accuracy: 0.4235 - loss: 1.2702 - val_accuracy: 0.4156 - val_loss: 1.2177\n",
            "Epoch 29/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 8s/step - accuracy: 0.4234 - loss: 1.2748 - val_accuracy: 0.3766 - val_loss: 1.2278\n",
            "Epoch 30/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.3978 - loss: 1.2315 - val_accuracy: 0.4675 - val_loss: 1.2393\n",
            "Epoch 31/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.4338 - loss: 1.2378 - val_accuracy: 0.5195 - val_loss: 1.2326\n",
            "Epoch 32/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 8s/step - accuracy: 0.3876 - loss: 1.2537 - val_accuracy: 0.4286 - val_loss: 1.2256\n",
            "Epoch 33/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 8s/step - accuracy: 0.4561 - loss: 1.2052 - val_accuracy: 0.4416 - val_loss: 1.2180\n",
            "Epoch 34/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4228 - loss: 1.2229 - val_accuracy: 0.5584 - val_loss: 1.2445\n",
            "Epoch 35/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 8s/step - accuracy: 0.4061 - loss: 1.2587 - val_accuracy: 0.5195 - val_loss: 1.2362\n",
            "Epoch 36/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 8s/step - accuracy: 0.4309 - loss: 1.2544 - val_accuracy: 0.6104 - val_loss: 1.2441\n",
            "Epoch 37/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 8s/step - accuracy: 0.3931 - loss: 1.2730 - val_accuracy: 0.5844 - val_loss: 1.2389\n",
            "Epoch 38/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.4154 - loss: 1.2390 - val_accuracy: 0.6104 - val_loss: 1.2308\n",
            "Epoch 39/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 8s/step - accuracy: 0.3884 - loss: 1.2532 - val_accuracy: 0.6104 - val_loss: 1.2323\n",
            "Epoch 40/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 8s/step - accuracy: 0.4375 - loss: 1.2654 - val_accuracy: 0.4026 - val_loss: 1.2103\n",
            "Epoch 41/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4464 - loss: 1.2252 - val_accuracy: 0.5325 - val_loss: 1.2221\n",
            "Epoch 42/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 8s/step - accuracy: 0.3513 - loss: 1.2619 - val_accuracy: 0.5844 - val_loss: 1.2218\n",
            "Epoch 43/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 8s/step - accuracy: 0.4576 - loss: 1.2335 - val_accuracy: 0.4935 - val_loss: 1.2489\n",
            "Epoch 44/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 8s/step - accuracy: 0.4588 - loss: 1.2261 - val_accuracy: 0.4935 - val_loss: 1.2020\n",
            "Epoch 45/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4870 - loss: 1.2169 - val_accuracy: 0.5974 - val_loss: 1.2097\n",
            "Epoch 46/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4841 - loss: 1.2125 - val_accuracy: 0.5974 - val_loss: 1.1938\n",
            "Epoch 47/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 8s/step - accuracy: 0.4373 - loss: 1.2607 - val_accuracy: 0.4545 - val_loss: 1.1941\n",
            "Epoch 48/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 8s/step - accuracy: 0.4558 - loss: 1.2439 - val_accuracy: 0.4156 - val_loss: 1.1971\n",
            "Epoch 49/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m146s\u001b[0m 8s/step - accuracy: 0.4504 - loss: 1.2326 - val_accuracy: 0.6104 - val_loss: 1.2148\n",
            "Epoch 50/50\n",
            "\u001b[1m17/17\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 8s/step - accuracy: 0.4468 - loss: 1.2201 - val_accuracy: 0.4935 - val_loss: 1.2298\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = model_resnet50.predict(test_gen)\n",
        "y_true = test_gen.classes\n",
        "y_pred_classes = np.argmax(y_pred, axis=1)\n",
        "\n",
        "# Evaluate the model\n",
        "def evaluate_model(model_name, y_true, y_pred_classes):\n",
        "    labels = list(test_gen.class_indices.keys())\n",
        "    accuracy = accuracy_score(y_true, y_pred_classes)\n",
        "    precision = precision_score(y_true, y_pred_classes, average='weighted')\n",
        "    recall = recall_score(y_true, y_pred_classes, average='weighted')\n",
        "    f1 = f1_score(y_true, y_pred_classes, average='weighted')\n",
        "    cm = confusion_matrix(y_true, y_pred_classes)\n",
        "\n",
        "    print(\"Accuracy:\", accuracy)\n",
        "    print(\"Precision:\", precision)\n",
        "    print(\"Recall:\", recall)\n",
        "    print(\"F1-score:\", f1)\n",
        "\n",
        "    print(\"Classification Report:\")\n",
        "    print(classification_report(y_true, y_pred_classes, target_names=labels))\n",
        "\n",
        "    # Plot confusion matrix\n",
        "    plt.figure(figsize=(6, 5))\n",
        "    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=labels, yticklabels=labels)\n",
        "    plt.xlabel(\"Predicted Label\")\n",
        "    plt.ylabel(\"True Label\")\n",
        "    plt.title(\"Confusion Matrix\")\n",
        "    plt.show()\n",
        "\n",
        "evaluate_model('ResNet50', y_true, y_pred_classes)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 941
        },
        "id": "GqZBj47zSH2N",
        "outputId": "c0afa0c1-4f3a-4d85-b948-2034d2419934"
      },
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m5/5\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 7s/step\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy: 0.46153846153846156\n",
            "Precision: 0.3763111888111888\n",
            "Recall: 0.46153846153846156\n",
            "F1-score: 0.3905899925317401\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "  Chickenpox       0.00      0.00      0.00        22\n",
            "     Measles       0.00      0.00      0.00        19\n",
            "   Monkeypox       0.40      0.80      0.54        56\n",
            "      Normal       0.61      0.46      0.52        59\n",
            "\n",
            "    accuracy                           0.46       156\n",
            "   macro avg       0.25      0.32      0.26       156\n",
            "weighted avg       0.38      0.46      0.39       156\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot training & validation accuracy values\n",
        "plt.figure(figsize=(12, 5))\n",
        "\n",
        "# Accuracy curve\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(history.history['accuracy'], label='Train Accuracy')\n",
        "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.title('Model Accuracy')\n",
        "plt.legend()\n",
        "\n",
        "# Loss curve\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(history.history['loss'], label='Train Loss')\n",
        "plt.plot(history.history['val_loss'], label='Validation Loss')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Loss')\n",
        "plt.title('Model Loss')\n",
        "plt.legend()\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "X5RaBH75tov3",
        "outputId": "d45f2f82-fbd1-40cc-9672-3d39034bb6dd"
      },
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_resnet50.save('monkeypox_resnet50_model.h5')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w8mzApdZtwPR",
        "outputId": "7e6ba5d1-7446-4964-fd08-ff77d323681e"
      },
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        }
      ]
    }
  ]
}