{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 90
        },
        "id": "12j7kz1dzx-G",
        "outputId": "9ee3c8e9-46a2-469c-892d-3908c58f6b5b"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-4c9ef622-2ac5-4c6a-aa47-cbf9962a3e60\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-4c9ef622-2ac5-4c6a-aa47-cbf9962a3e60\">\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 kaggle.json to kaggle.json\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'kaggle.json': b'{\"username\":\"aditiijaiz\",\"key\":\"f2a0697e808938fe7952f5d14e693620\"}'}"
            ]
          },
          "metadata": {},
          "execution_count": 1
        }
      ],
      "source": [
        "# Install kaggle\n",
        "!pip install -q kaggle\n",
        "\n",
        "from google.colab import files\n",
        "files.upload()  # upload kaggle.json file here"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "w6g7CIATz1C4"
      },
      "outputs": [],
      "source": [
        "# Configure kaggle credentials\n",
        "!mkdir -p ~/.kaggle\n",
        "!cp kaggle.json ~/.kaggle/\n",
        "!chmod 600 ~/.kaggle/kaggle.json"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "O1NlDHpoz2YC",
        "outputId": "af1eb679-a2a9-4932-b93d-eccd9e2bc6b1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Warning: Looks like you're using an outdated `kaggle` version (installed: 2.0.2), please consider upgrading to the latest version (2.2.2)\n",
            "Dataset URL: https://www.kaggle.com/datasets/gpiosenka/plant-pathology-2021resized-512-x-512\n",
            "License(s): unknown\n",
            "Downloading plant-pathology-2021resized-512-x-512.zip to /content\n",
            "100% 1.88G/1.88G [00:58<00:00, 34.5MB/s]\n",
            "\n"
          ]
        }
      ],
      "source": [
        "# Download dataset\n",
        "!kaggle datasets download -d gpiosenka/plant-pathology-2021resized-512-x-512\n",
        "\n",
        "# Unzip\n",
        "!mkdir -p plant_data\n",
        "!unzip -q plant-pathology-2021resized-512-x-512.zip -d plant_data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NgwyaWNZ0dXX",
        "outputId": "8496a6c7-ab6f-4399-ccf3-5021f778e9a7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            " data.csv   images  'plants-12-(256 X 256)-84.74.h5'\n"
          ]
        }
      ],
      "source": [
        "!ls plant_data"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oreNPRw-0pN4"
      },
      "source": [
        "# Inspect the CSV"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 397
        },
        "id": "8Vnos4WZ0lxw",
        "outputId": "18543e1a-0060-4a20-855a-ae05a3424a69"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(18632, 4)\n",
            "['Unnamed: 0', 'filepaths', 'labels', 'data set']\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Unnamed: 0             filepaths                           labels data set\n",
              "0           0  800113bb65efe69e.jpg                          healthy    train\n",
              "1           0  8002cb321f8bfcdf.jpg  scab frog_eye_leaf_spot complex    train\n",
              "2           0  80070f7fb5e2ccaa.jpg                             scab    train\n",
              "3           0  80077517781fb94f.jpg                             scab    train\n",
              "4           0  800cbf0ff87721f8.jpg                          complex    train\n",
              "5           0  800edef467d27c15.jpg                          healthy    train\n",
              "6           0  800f85dc5f407aef.jpg                             rust    train\n",
              "7           0  801d6dcd96e48ebc.jpg                          healthy    train\n",
              "8           0  801f78399a44e7af.jpg                          complex    train\n",
              "9           0  8021b94d437eb7d3.jpg                          healthy    train"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-42999d18-db99-46ad-95da-ad35cc9e99d2\" 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>Unnamed: 0</th>\n",
              "      <th>filepaths</th>\n",
              "      <th>labels</th>\n",
              "      <th>data set</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>800113bb65efe69e.jpg</td>\n",
              "      <td>healthy</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>8002cb321f8bfcdf.jpg</td>\n",
              "      <td>scab frog_eye_leaf_spot complex</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0</td>\n",
              "      <td>80070f7fb5e2ccaa.jpg</td>\n",
              "      <td>scab</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "      <td>80077517781fb94f.jpg</td>\n",
              "      <td>scab</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>800cbf0ff87721f8.jpg</td>\n",
              "      <td>complex</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0</td>\n",
              "      <td>800edef467d27c15.jpg</td>\n",
              "      <td>healthy</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0</td>\n",
              "      <td>800f85dc5f407aef.jpg</td>\n",
              "      <td>rust</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0</td>\n",
              "      <td>801d6dcd96e48ebc.jpg</td>\n",
              "      <td>healthy</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>0</td>\n",
              "      <td>801f78399a44e7af.jpg</td>\n",
              "      <td>complex</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0</td>\n",
              "      <td>8021b94d437eb7d3.jpg</td>\n",
              "      <td>healthy</td>\n",
              "      <td>train</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-42999d18-db99-46ad-95da-ad35cc9e99d2')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-42999d18-db99-46ad-95da-ad35cc9e99d2 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-42999d18-db99-46ad-95da-ad35cc9e99d2');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 18632,\n  \"fields\": [\n    {\n      \"column\": \"Unnamed: 0\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"filepaths\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 18632,\n        \"samples\": [\n          \"ae7a52cc3cc3241f.jpg\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"labels\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 12,\n        \"samples\": [\n          \"powdery_mildew complex\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"data set\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"train\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "import pandas as pd\n",
        "\n",
        "df = pd.read_csv('plant_data/data.csv')\n",
        "print(df.shape)\n",
        "print(df.columns.tolist())\n",
        "df.head(10)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H9qmiC050__0",
        "outputId": "f3dae962-932b-4df0-8adf-f5bf7c4781e4"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "labels\n",
            "scab                               4826\n",
            "healthy                            4624\n",
            "frog_eye_leaf_spot                 3181\n",
            "rust                               1860\n",
            "complex                            1602\n",
            "powdery_mildew                     1184\n",
            "scab frog_eye_leaf_spot             686\n",
            "scab frog_eye_leaf_spot complex     200\n",
            "frog_eye_leaf_spot complex          165\n",
            "rust frog_eye_leaf_spot             120\n",
            "rust complex                         97\n",
            "powdery_mildew complex               87\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Number of unique label combinations: 12\n",
            "\n",
            " data set\n",
            "train    16632\n",
            "test      1000\n",
            "valid     1000\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Individual classes:\n",
            " labels\n",
            "scab                  5712\n",
            "healthy               4624\n",
            "frog_eye_leaf_spot    4352\n",
            "complex               2151\n",
            "rust                  2077\n",
            "powdery_mildew        1271\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# Check unique label combinations and their counts\n",
        "print(df['labels'].value_counts())\n",
        "print(\"\\nNumber of unique label combinations:\", df['labels'].nunique())\n",
        "\n",
        "# Check train/valid/test split sizes\n",
        "print(\"\\n\", df['data set'].value_counts())\n",
        "\n",
        "# Check individual disease classes (split by space)\n",
        "all_labels = df['labels'].str.split(' ').explode()\n",
        "print(\"\\nIndividual classes:\\n\", all_labels.value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IVagKEVS1AmI",
        "outputId": "29ed8a84-53e6-48d1-a620-c83f1fcd0914"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Filtered dataset shape: (15675, 4)\n",
            "\n",
            "Class distribution:\n",
            " labels\n",
            "scab                  4826\n",
            "healthy               4624\n",
            "frog_eye_leaf_spot    3181\n",
            "rust                  1860\n",
            "powdery_mildew        1184\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Split distribution:\n",
            " data set\n",
            "train    13984\n",
            "test       859\n",
            "valid      832\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Class distribution within each split:\n",
            " data set  labels            \n",
            "test      healthy                347\n",
            "          scab                   252\n",
            "          frog_eye_leaf_spot     133\n",
            "          rust                    91\n",
            "          powdery_mildew          36\n",
            "train     scab                  4365\n",
            "          healthy               3990\n",
            "          frog_eye_leaf_spot    2872\n",
            "          rust                  1665\n",
            "          powdery_mildew        1092\n",
            "valid     healthy                287\n",
            "          scab                   209\n",
            "          frog_eye_leaf_spot     176\n",
            "          rust                   104\n",
            "          powdery_mildew          56\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# Filter to the 5 target classes\n",
        "target_classes = ['healthy', 'scab', 'frog_eye_leaf_spot', 'rust', 'powdery_mildew']\n",
        "\n",
        "# Keep only rows where the label is EXACTLY one of these 5 classes (no combinations)\n",
        "df_filtered = df[df['labels'].isin(target_classes)].reset_index(drop=True)\n",
        "\n",
        "print(\"Filtered dataset shape:\", df_filtered.shape)\n",
        "print(\"\\nClass distribution:\\n\", df_filtered['labels'].value_counts())\n",
        "print(\"\\nSplit distribution:\\n\", df_filtered['data set'].value_counts())\n",
        "print(\"\\nClass distribution within each split:\\n\",\n",
        "      df_filtered.groupby('data set')['labels'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qg3Fq8LC1eVa",
        "outputId": "7e3e1e5d-a7c6-48e3-972b-fec581ab0ccb"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Sample path: plant_data/images/800113bb65efe69e.jpg\n",
            "Exists? True\n",
            "\n",
            "Train: (13984, 5) Valid: (832, 5) Test: (859, 5)\n"
          ]
        }
      ],
      "source": [
        "# Build full image paths and encode labels\n",
        "import os\n",
        "\n",
        "IMAGE_DIR = 'plant_data/images'\n",
        "\n",
        "# Build full path column\n",
        "df_filtered['full_path'] = df_filtered['filepaths'].apply(lambda x: os.path.join(IMAGE_DIR, x))\n",
        "\n",
        "# Sanity check: do these files actually exist?\n",
        "print(\"Sample path:\", df_filtered['full_path'].iloc[0])\n",
        "print(\"Exists?\", os.path.exists(df_filtered['full_path'].iloc[0]))\n",
        "\n",
        "# Split into train/valid/test based on existing 'data set' column\n",
        "train_df = df_filtered[df_filtered['data set'] == 'train'].reset_index(drop=True)\n",
        "valid_df = df_filtered[df_filtered['data set'] == 'valid'].reset_index(drop=True)\n",
        "test_df  = df_filtered[df_filtered['data set'] == 'test'].reset_index(drop=True)\n",
        "\n",
        "print(\"\\nTrain:\", train_df.shape, \"Valid:\", valid_df.shape, \"Test:\", test_df.shape)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install tensorflow"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Z73gEPyL-m-j",
        "outputId": "09681bf2-e386-48e2-ba77-fa7e4b0437e8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting tensorflow\n",
            "  Downloading tensorflow-2.21.0-cp312-cp312-manylinux_2_27_x86_64.whl.metadata (4.4 kB)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.4.0)\n",
            "Collecting astunparse>=1.6.0 (from tensorflow)\n",
            "  Downloading astunparse-1.6.3-py2.py3-none-any.whl.metadata (4.4 kB)\n",
            "Collecting flatbuffers>=25.9.23 (from tensorflow)\n",
            "  Downloading flatbuffers-25.12.19-py2.py3-none-any.whl.metadata (1.0 kB)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.7.0)\n",
            "Collecting google_pasta>=0.1.1 (from tensorflow)\n",
            "  Downloading google_pasta-0.2.0-py3-none-any.whl.metadata (814 bytes)\n",
            "Collecting libclang>=13.0.0 (from tensorflow)\n",
            "  Downloading libclang-18.1.1-py2.py3-none-manylinux2010_x86_64.whl.metadata (5.2 kB)\n",
            "Requirement already satisfied: opt_einsum>=2.3.2 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.4.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from tensorflow) (26.2)\n",
            "Requirement already satisfied: protobuf<8.0.0,>=6.31.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (7.35.1)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.32.4)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from tensorflow) (75.2.0)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.17.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.3.0)\n",
            "Requirement already satisfied: typing_extensions>=3.6.6 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (4.15.0)\n",
            "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.2.2)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.81.1)\n",
            "Requirement already satisfied: keras>=3.12.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.13.2)\n",
            "Requirement already satisfied: numpy>=1.26.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.0.2)\n",
            "Collecting h5py<3.15.0,>=3.11.0 (from tensorflow)\n",
            "  Downloading h5py-3.14.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.7 kB)\n",
            "Requirement already satisfied: ml_dtypes<1.0.0,>=0.5.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.5.4)\n",
            "Collecting wheel<1.0,>=0.23.0 (from astunparse>=1.6.0->tensorflow)\n",
            "  Downloading wheel-0.47.0-py3-none-any.whl.metadata (2.3 kB)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from keras>=3.12.0->tensorflow) (15.0.0)\n",
            "Requirement already satisfied: namex in /usr/local/lib/python3.12/dist-packages (from keras>=3.12.0->tensorflow) (0.1.0)\n",
            "Requirement already satisfied: optree in /usr/local/lib/python3.12/dist-packages (from keras>=3.12.0->tensorflow) (0.19.1)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.4.7)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.18)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (2026.6.17)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->keras>=3.12.0->tensorflow) (4.2.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->keras>=3.12.0->tensorflow) (2.20.0)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->keras>=3.12.0->tensorflow) (0.1.2)\n",
            "Downloading tensorflow-2.21.0-cp312-cp312-manylinux_2_27_x86_64.whl (572.6 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m572.6/572.6 MB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)\n",
            "Downloading flatbuffers-25.12.19-py2.py3-none-any.whl (26 kB)\n",
            "Downloading google_pasta-0.2.0-py3-none-any.whl (57 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.5/57.5 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading h5py-3.14.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.9 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.9/4.9 MB\u001b[0m \u001b[31m190.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading libclang-18.1.1-py2.py3-none-manylinux2010_x86_64.whl (24.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.5/24.5 MB\u001b[0m \u001b[31m160.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading wheel-0.47.0-py3-none-any.whl (32 kB)\n",
            "Installing collected packages: libclang, flatbuffers, wheel, h5py, google_pasta, astunparse, tensorflow\n",
            "  Attempting uninstall: h5py\n",
            "    Found existing installation: h5py 3.16.0\n",
            "    Uninstalling h5py-3.16.0:\n",
            "      Successfully uninstalled h5py-3.16.0\n",
            "Successfully installed astunparse-1.6.3 flatbuffers-25.12.19 google_pasta-0.2.0 h5py-3.14.0 libclang-18.1.1 tensorflow-2.21.0 wheel-0.47.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ayNnm_VP1pUl",
        "outputId": "f236adcd-ef61-41c0-b9e8-b2e1d804a623"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/jax/_src/cloud_tpu_init.py:86: UserWarning: Transparent hugepages are not enabled. TPU runtime startup and shutdown time should be significantly improved on TPU v5e and newer. If not already set, you may need to enable transparent hugepages in your VM image (sudo sh -c \"echo always > /sys/kernel/mm/transparent_hugepage/enabled\")\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 13984 validated image filenames belonging to 5 classes.\n",
            "Found 832 validated image filenames belonging to 5 classes.\n",
            "Found 859 validated image filenames belonging to 5 classes.\n",
            "{'frog_eye_leaf_spot': 0, 'healthy': 1, 'powdery_mildew': 2, 'rust': 3, 'scab': 4}\n"
          ]
        }
      ],
      "source": [
        "# ImageDataGenerator with augmentation\n",
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "IMG_SIZE = (128, 128)   # we'll start smaller for faster training, can increase later\n",
        "BATCH_SIZE = 32\n",
        "\n",
        "# Training generator: with augmentation\n",
        "train_datagen = ImageDataGenerator(\n",
        "    rescale=1./255,\n",
        "    rotation_range=20,\n",
        "    width_shift_range=0.1,\n",
        "    height_shift_range=0.1,\n",
        "    shear_range=0.1,\n",
        "    zoom_range=0.15,\n",
        "    horizontal_flip=True,\n",
        "    fill_mode='nearest'\n",
        ")\n",
        "\n",
        "# Validation/Test generator: only rescaling, no augmentation\n",
        "valid_test_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "train_generator = train_datagen.flow_from_dataframe(\n",
        "    dataframe=train_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=True,\n",
        "    seed=42\n",
        ")\n",
        "\n",
        "valid_generator = valid_test_datagen.flow_from_dataframe(\n",
        "    dataframe=valid_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "test_generator = valid_test_datagen.flow_from_dataframe(\n",
        "    dataframe=test_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "# Check class label mapping\n",
        "print(train_generator.class_indices)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xfERm9Nz1y1E",
        "outputId": "8427a64a-4710-4289-e394-1212c7525a37"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "{0: np.float64(0.973816155988858), 1: np.float64(0.700952380952381), 2: np.float64(2.561172161172161), 3: np.float64(1.6797597597597598), 4: np.float64(0.6407331042382589)}\n"
          ]
        }
      ],
      "source": [
        "# Class Weights\n",
        "import numpy as np\n",
        "from sklearn.utils.class_weight import compute_class_weight\n",
        "\n",
        "# Get integer labels for train set in the same order as class_indices\n",
        "class_labels = list(train_generator.class_indices.keys())\n",
        "train_classes = train_df['labels'].map(train_generator.class_indices).values\n",
        "\n",
        "class_weights_array = compute_class_weight(\n",
        "    class_weight='balanced',\n",
        "    classes=np.unique(train_classes),\n",
        "    y=train_classes\n",
        ")\n",
        "\n",
        "class_weights = dict(enumerate(class_weights_array))\n",
        "print(class_weights)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 824
        },
        "id": "hWygSXRs1z6N",
        "outputId": "92441308-d54b-4b42-c093-75d90a276ca7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
            "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m128\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │           \u001b[38;5;34m256\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_2           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │           \u001b[38;5;34m512\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m295,168\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_3           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │         \u001b[38;5;34m1,024\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16384\u001b[0m)          │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │     \u001b[38;5;34m4,194,560\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m)              │           \u001b[38;5;34m645\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_2           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_3           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16384</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │     <span style=\"color: #00af00; text-decoration-color: #00af00\">4,194,560</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">645</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,618,437\u001b[0m (17.62 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,618,437</span> (17.62 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m4,617,477\u001b[0m (17.61 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,617,477</span> (17.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m960\u001b[0m (3.75 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">960</span> (3.75 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Build the CNN model\n",
        "from tensorflow.keras import layers, models\n",
        "\n",
        "def build_cnn(input_shape=(128,128,3), num_classes=5, dropout_rate=0.3):\n",
        "    model = models.Sequential([\n",
        "        layers.Conv2D(32, (3,3), activation='relu', padding='same', input_shape=input_shape),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Conv2D(64, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Conv2D(128, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Conv2D(256, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Flatten(),\n",
        "        layers.Dense(256, activation='relu'),\n",
        "        layers.Dropout(dropout_rate),\n",
        "        layers.Dense(128, activation='relu'),\n",
        "        layers.Dropout(dropout_rate),\n",
        "        layers.Dense(num_classes, activation='softmax')\n",
        "    ])\n",
        "    return model\n",
        "\n",
        "model = build_cnn()\n",
        "model.summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "inURUG5d1914"
      },
      "outputs": [],
      "source": [
        "# Compile the model\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "\n",
        "LEARNING_RATE = 0.001\n",
        "\n",
        "model.compile(\n",
        "    optimizer=Adam(learning_rate=LEARNING_RATE),\n",
        "    loss='categorical_crossentropy',\n",
        "    metrics=['accuracy']\n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "OdB_zKOb2MNJ"
      },
      "outputs": [],
      "source": [
        "# Setup call backs\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n",
        "\n",
        "early_stop = EarlyStopping(\n",
        "    monitor='val_loss',\n",
        "    patience=5,\n",
        "    restore_best_weights=True\n",
        ")\n",
        "\n",
        "checkpoint = ModelCheckpoint(\n",
        "    'best_model.keras',\n",
        "    monitor='val_accuracy',\n",
        "    save_best_only=True\n",
        ")\n",
        "\n",
        "reduce_lr = ReduceLROnPlateau(\n",
        "    monitor='val_loss',\n",
        "    factor=0.5,\n",
        "    patience=3,\n",
        "    min_lr=1e-6\n",
        ")\n",
        "\n",
        "callbacks_list = [early_stop, checkpoint, reduce_lr]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "smi7hFUM2NRJ",
        "outputId": "1da31ce5-139a-4050-a1cf-06be6f92a003"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 159ms/step - accuracy: 0.3539 - loss: 1.7587 - val_accuracy: 0.3618 - val_loss: 1.3349 - learning_rate: 0.0010\n",
            "Epoch 2/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 163ms/step - accuracy: 0.4133 - loss: 1.1891 - val_accuracy: 0.2212 - val_loss: 2.6615 - learning_rate: 0.0010\n",
            "Epoch 3/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 160ms/step - accuracy: 0.4681 - loss: 1.0896 - val_accuracy: 0.3209 - val_loss: 1.6034 - learning_rate: 0.0010\n",
            "Epoch 4/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 159ms/step - accuracy: 0.5501 - loss: 0.9698 - val_accuracy: 0.4904 - val_loss: 1.1843 - learning_rate: 0.0010\n",
            "Epoch 5/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 157ms/step - accuracy: 0.6222 - loss: 0.8195 - val_accuracy: 0.5288 - val_loss: 1.3363 - learning_rate: 0.0010\n",
            "Epoch 6/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 159ms/step - accuracy: 0.6495 - loss: 0.7424 - val_accuracy: 0.7139 - val_loss: 0.6689 - learning_rate: 0.0010\n",
            "Epoch 7/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 158ms/step - accuracy: 0.6771 - loss: 0.6571 - val_accuracy: 0.7139 - val_loss: 0.6753 - learning_rate: 0.0010\n",
            "Epoch 8/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 158ms/step - accuracy: 0.7031 - loss: 0.6336 - val_accuracy: 0.6238 - val_loss: 0.8476 - learning_rate: 0.0010\n",
            "Epoch 9/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 159ms/step - accuracy: 0.7497 - loss: 0.5648 - val_accuracy: 0.4724 - val_loss: 2.2041 - learning_rate: 0.0010\n",
            "Epoch 10/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 161ms/step - accuracy: 0.8216 - loss: 0.4437 - val_accuracy: 0.8221 - val_loss: 0.5489 - learning_rate: 5.0000e-04\n",
            "Epoch 11/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m69s\u001b[0m 158ms/step - accuracy: 0.8389 - loss: 0.3922 - val_accuracy: 0.8462 - val_loss: 0.4309 - learning_rate: 5.0000e-04\n",
            "Epoch 12/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 157ms/step - accuracy: 0.8561 - loss: 0.3679 - val_accuracy: 0.7825 - val_loss: 0.5713 - learning_rate: 5.0000e-04\n",
            "Epoch 13/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 160ms/step - accuracy: 0.8714 - loss: 0.3329 - val_accuracy: 0.8702 - val_loss: 0.4258 - learning_rate: 5.0000e-04\n",
            "Epoch 14/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 156ms/step - accuracy: 0.8731 - loss: 0.3341 - val_accuracy: 0.8834 - val_loss: 0.3520 - learning_rate: 5.0000e-04\n",
            "Epoch 15/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 160ms/step - accuracy: 0.8837 - loss: 0.3048 - val_accuracy: 0.8822 - val_loss: 0.3225 - learning_rate: 5.0000e-04\n"
          ]
        }
      ],
      "source": [
        "# Train the model\n",
        "EPOCHS = 15\n",
        "\n",
        "history = model.fit(\n",
        "    train_generator,\n",
        "    steps_per_epoch=len(train_generator),\n",
        "    validation_data=valid_generator,\n",
        "    validation_steps=len(valid_generator),\n",
        "    epochs=EPOCHS,\n",
        "    class_weight=class_weights,\n",
        "    callbacks=callbacks_list\n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "8tqDE-iT2REt",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "outputId": "59eed9ad-6ae2-4d23-a47f-8e2f4ce0fb8a"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "#  Plot loss and accuracy curves\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "acc = history.history['accuracy']\n",
        "val_acc = history.history['val_accuracy']\n",
        "loss = history.history['loss']\n",
        "val_loss = history.history['val_loss']\n",
        "epochs_range = range(1, len(acc) + 1)\n",
        "\n",
        "plt.figure(figsize=(14, 5))\n",
        "\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(epochs_range, acc, label='Train Accuracy')\n",
        "plt.plot(epochs_range, val_acc, label='Validation Accuracy')\n",
        "plt.title('Accuracy Curve')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(epochs_range, loss, label='Train Loss')\n",
        "plt.plot(epochs_range, val_loss, label='Validation Loss')\n",
        "plt.title('Loss Curve')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predict on test set\n",
        "import numpy as np\n",
        "\n",
        "test_generator.reset()\n",
        "\n",
        "y_pred_probs = model.predict(test_generator, steps=len(test_generator), verbose=1)\n",
        "y_pred = np.argmax(y_pred_probs, axis=1)\n",
        "\n",
        "y_true = test_generator.classes\n",
        "y_true = np.array(y_true) # Convert to numpy array to use .shape\n",
        "\n",
        "class_labels = list(test_generator.class_indices.keys())\n",
        "print(\"Class labels order:\", class_labels)\n",
        "print(\"Predicted shape:\", y_pred.shape, \"True shape:\", y_true.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Pg-1iGRzDUME",
        "outputId": "88702979-a261-4397-da9d-a6e81b03d7e6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 65ms/step\n",
            "Class labels order: ['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n",
            "Predicted shape: (859,) True shape: (859,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Classification report\n",
        "from sklearn.metrics import classification_report, accuracy_score\n",
        "\n",
        "print(\"Test Accuracy:\", accuracy_score(y_true, y_pred))\n",
        "print(\"\\nClassification Report:\\n\")\n",
        "print(classification_report(y_true, y_pred, target_names=class_labels, digits=4))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "u3cwBOLYDYx0",
        "outputId": "abc9c2a0-b27d-4795-c844-f0b74927a30b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Accuracy: 0.8754365541327125\n",
            "\n",
            "Classification Report:\n",
            "\n",
            "                    precision    recall  f1-score   support\n",
            "\n",
            "frog_eye_leaf_spot     0.9214    0.9699    0.9451       133\n",
            "           healthy     0.8038    0.9798    0.8831       347\n",
            "    powdery_mildew     0.8438    0.7500    0.7941        36\n",
            "              rust     0.9579    1.0000    0.9785        91\n",
            "              scab     0.9763    0.6548    0.7838       252\n",
            "\n",
            "          accuracy                         0.8754       859\n",
            "         macro avg     0.9006    0.8709    0.8769       859\n",
            "      weighted avg     0.8906    0.8754    0.8700       859\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Confusion Matrix\n",
        "from sklearn.metrics import confusion_matrix\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "cm = confusion_matrix(y_true, y_pred)\n",
        "\n",
        "plt.figure(figsize=(8, 6))\n",
        "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n",
        "            xticklabels=class_labels, yticklabels=class_labels)\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('Actual')\n",
        "plt.title('Confusion Matrix')\n",
        "plt.savefig('confusion_matrix.png')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "id": "rbV6TRw4DiyD",
        "outputId": "75b6e871-a597-4a86-e66c-47d697a68e26"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Deeper CNN"
      ],
      "metadata": {
        "id": "OvMzDArmFHY0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Build Model 2 — deeper CNN with tuned hyperparameters\n",
        "from tensorflow.keras import layers, models, regularizers\n",
        "from tensorflow.keras.optimizers import RMSprop\n",
        "\n",
        "def build_cnn_v2(input_shape=(128,128,3), num_classes=5, dropout_rate=0.4):\n",
        "    model = models.Sequential([\n",
        "        layers.Conv2D(32, (3,3), activation='relu', padding='same', input_shape=input_shape),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.Conv2D(32, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Conv2D(64, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.Conv2D(64, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Conv2D(128, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.Conv2D(128, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.Conv2D(256, (3,3), activation='relu', padding='same'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.MaxPooling2D(2,2),\n",
        "\n",
        "        layers.GlobalAveragePooling2D(),   # replaces Flatten -> fewer params, less overfitting\n",
        "        layers.Dense(256, activation='relu', kernel_regularizer=regularizers.l2(1e-4)),\n",
        "        layers.Dropout(dropout_rate),\n",
        "        layers.Dense(128, activation='relu', kernel_regularizer=regularizers.l2(1e-4)),\n",
        "        layers.Dropout(dropout_rate),\n",
        "        layers.Dense(num_classes, activation='softmax')\n",
        "    ])\n",
        "    return model\n",
        "\n",
        "model2 = build_cnn_v2()\n",
        "model2.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "UJ2JxasAFJKf",
        "outputId": "d85981ea-0d4f-46ff-c713-fe3fdc4a8d7e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_1\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_4           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m128\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │         \u001b[38;5;34m9,248\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_5           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m128\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_6           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │           \u001b[38;5;34m256\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m36,928\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_7           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │           \u001b[38;5;34m256\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_5 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_8 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_8           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │           \u001b[38;5;34m512\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_9 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │       \u001b[38;5;34m147,584\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_9           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │           \u001b[38;5;34m512\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_6 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m)              │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m295,168\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_10          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │         \u001b[38;5;34m1,024\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_7 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │        \u001b[38;5;34m65,792\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_4 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_5 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m)              │           \u001b[38;5;34m645\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_4           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │         <span style=\"color: #00af00; text-decoration-color: #00af00\">9,248</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_5           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_6           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">36,928</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_7           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_8           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">147,584</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_9           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)              │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_10          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">65,792</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">645</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m684,325\u001b[0m (2.61 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">684,325</span> (2.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m682,917\u001b[0m (2.61 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">682,917</span> (2.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m1,408\u001b[0m (5.50 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,408</span> (5.50 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Stronger augmentation\n",
        "train_datagen_v2 = ImageDataGenerator(\n",
        "    rescale=1./255,\n",
        "    rotation_range=30,\n",
        "    width_shift_range=0.15,\n",
        "    height_shift_range=0.15,\n",
        "    shear_range=0.15,\n",
        "    zoom_range=0.2,\n",
        "    horizontal_flip=True,\n",
        "    vertical_flip=True,\n",
        "    brightness_range=[0.8, 1.2],\n",
        "    fill_mode='nearest'\n",
        ")\n",
        "\n",
        "train_generator_v2 = train_datagen_v2.flow_from_dataframe(\n",
        "    dataframe=train_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=True,\n",
        "    seed=42\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jbzqM6DBFO6Y",
        "outputId": "9b9dabca-7e7e-473e-f122-4bbea5d957f1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 13984 validated image filenames belonging to 5 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Compile Model\n",
        "model2.compile(\n",
        "    optimizer=RMSprop(learning_rate=0.0005),\n",
        "    loss='categorical_crossentropy',\n",
        "    metrics=['accuracy']\n",
        ")"
      ],
      "metadata": {
        "id": "pESqZl0mFTaH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Callbacks\n",
        "early_stop_v2 = EarlyStopping(monitor='val_loss', patience=6, restore_best_weights=True)\n",
        "checkpoint_v2 = ModelCheckpoint('best_model_v2.keras', monitor='val_accuracy', save_best_only=True)\n",
        "reduce_lr_v2 = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3, min_lr=1e-6)\n",
        "\n",
        "callbacks_v2 = [early_stop_v2, checkpoint_v2, reduce_lr_v2]"
      ],
      "metadata": {
        "id": "jSQ0uH8JFWHJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Train Model\n",
        "EPOCHS_V2 = 15\n",
        "\n",
        "history2 = model2.fit(\n",
        "    train_generator_v2,\n",
        "    steps_per_epoch=len(train_generator_v2),\n",
        "    validation_data=valid_generator,\n",
        "    validation_steps=len(valid_generator),\n",
        "    epochs=EPOCHS_V2,\n",
        "    class_weight=class_weights,\n",
        "    callbacks=callbacks_v2\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "K7Q33H1lFYpM",
        "outputId": "abe21cdc-4967-4e85-b4bd-77874815b853"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m98s\u001b[0m 220ms/step - accuracy: 0.4136 - loss: 1.3355 - val_accuracy: 0.2897 - val_loss: 1.7542 - learning_rate: 5.0000e-04\n",
            "Epoch 2/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m96s\u001b[0m 219ms/step - accuracy: 0.6314 - loss: 0.8748 - val_accuracy: 0.3594 - val_loss: 2.3140 - learning_rate: 5.0000e-04\n",
            "Epoch 3/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 215ms/step - accuracy: 0.7493 - loss: 0.6646 - val_accuracy: 0.6839 - val_loss: 0.9934 - learning_rate: 5.0000e-04\n",
            "Epoch 4/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 215ms/step - accuracy: 0.8368 - loss: 0.5261 - val_accuracy: 0.7200 - val_loss: 0.8511 - learning_rate: 5.0000e-04\n",
            "Epoch 5/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 216ms/step - accuracy: 0.8704 - loss: 0.4227 - val_accuracy: 0.6550 - val_loss: 1.2344 - learning_rate: 5.0000e-04\n",
            "Epoch 6/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m96s\u001b[0m 218ms/step - accuracy: 0.8874 - loss: 0.3913 - val_accuracy: 0.8906 - val_loss: 0.3997 - learning_rate: 5.0000e-04\n",
            "Epoch 7/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m96s\u001b[0m 220ms/step - accuracy: 0.8941 - loss: 0.3689 - val_accuracy: 0.8413 - val_loss: 0.5806 - learning_rate: 5.0000e-04\n",
            "Epoch 8/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 215ms/step - accuracy: 0.8992 - loss: 0.3477 - val_accuracy: 0.8233 - val_loss: 0.5953 - learning_rate: 5.0000e-04\n",
            "Epoch 9/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m93s\u001b[0m 213ms/step - accuracy: 0.9001 - loss: 0.3420 - val_accuracy: 0.8834 - val_loss: 0.4073 - learning_rate: 5.0000e-04\n",
            "Epoch 10/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m96s\u001b[0m 219ms/step - accuracy: 0.9236 - loss: 0.2730 - val_accuracy: 0.8389 - val_loss: 0.5234 - learning_rate: 2.5000e-04\n",
            "Epoch 11/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m95s\u001b[0m 216ms/step - accuracy: 0.9291 - loss: 0.2615 - val_accuracy: 0.7500 - val_loss: 1.3278 - learning_rate: 2.5000e-04\n",
            "Epoch 12/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 215ms/step - accuracy: 0.9321 - loss: 0.2398 - val_accuracy: 0.8738 - val_loss: 0.4752 - learning_rate: 2.5000e-04\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Accuracy and Loss Curve\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "acc2 = history2.history['accuracy']\n",
        "val_acc2 = history2.history['val_accuracy']\n",
        "loss2 = history2.history['loss']\n",
        "val_loss2 = history2.history['val_loss']\n",
        "epochs_range2 = range(1, len(acc2) + 1)\n",
        "\n",
        "plt.figure(figsize=(14, 5))\n",
        "\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(epochs_range2, acc2, label='Train Accuracy')\n",
        "plt.plot(epochs_range2, val_acc2, label='Validation Accuracy')\n",
        "plt.title('Model 2 - Accuracy Curve')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(epochs_range2, loss2, label='Train Loss')\n",
        "plt.plot(epochs_range2, val_loss2, label='Validation Loss')\n",
        "plt.title('Model 2 - Loss Curve')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "id": "JPwgBvmZdI58",
        "outputId": "be8ff94d-0037-48ea-e8da-088b38ee75b4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predict on test set\n",
        "import numpy as np\n",
        "\n",
        "test_generator.reset()\n",
        "\n",
        "y_pred_probs2 = model2.predict(test_generator, steps=len(test_generator), verbose=1)\n",
        "y_pred2 = np.argmax(y_pred_probs2, axis=1)\n",
        "\n",
        "y_true2 = test_generator.classes\n",
        "y_true2 = np.array(y_true2) # Convert to numpy array to use .shape\n",
        "\n",
        "class_labels = list(test_generator.class_indices.keys())\n",
        "print(\"Class labels order:\", class_labels)\n",
        "print(\"Predicted shape: \", y_pred2.shape, \"True shape: \", y_true2.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "B0QCXBxudOvw",
        "outputId": "dff1e656-2982-4aaf-bb92-d6ff5e074330"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 70ms/step\n",
            "Class labels order: ['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n",
            "Predicted shape:  (859,) True shape:  (859,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Classification Report\n",
        "from sklearn.metrics import classification_report, accuracy_score\n",
        "\n",
        "print(\"Model Test Accuracy:\", accuracy_score(y_true2, y_pred2))\n",
        "print(\"\\nClassification Report:\\n\")\n",
        "print(classification_report(y_true2, y_pred2, target_names=class_labels, digits=4))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GH0L871HdYO4",
        "outputId": "4b48e964-363c-4d11-fd1f-2c8b7f4b460e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model Test Accuracy: 0.8975552968568102\n",
            "\n",
            "Classification Report:\n",
            "\n",
            "                    precision    recall  f1-score   support\n",
            "\n",
            "frog_eye_leaf_spot     0.9353    0.9774    0.9559       133\n",
            "           healthy     0.8403    0.9856    0.9072       347\n",
            "    powdery_mildew     0.8889    0.6667    0.7619        36\n",
            "              rust     0.9565    0.9670    0.9617        91\n",
            "              scab     0.9639    0.7421    0.8386       252\n",
            "\n",
            "          accuracy                         0.8976       859\n",
            "         macro avg     0.9170    0.8678    0.8851       859\n",
            "      weighted avg     0.9056    0.8976    0.8943       859\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Confusion Matrix\n",
        "from sklearn.metrics import confusion_matrix\n",
        "import seaborn as sns\n",
        "\n",
        "cm2 = confusion_matrix(y_true2, y_pred2)\n",
        "\n",
        "plt.figure(figsize=(8, 6))\n",
        "sns.heatmap(cm2, annot=True, fmt='d', cmap='Greens',\n",
        "            xticklabels=class_labels, yticklabels=class_labels)\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('Actual')\n",
        "plt.title('Confusion Matrix')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "id": "FGAyqvRfdfmI",
        "outputId": "47ef35da-2cd2-4bbf-efa6-799295827454"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# ANN"
      ],
      "metadata": {
        "id": "ViKgMcr3d-O5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Data generation for ANN\n",
        "# Reuse same IMG_SIZE and BATCH_SIZE, same augmentation as Model 1 for fair comparison\n",
        "train_generator_ann = train_datagen.flow_from_dataframe(\n",
        "    dataframe=train_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=True,\n",
        "    seed=42\n",
        ")\n",
        "\n",
        "valid_generator_ann = valid_test_datagen.flow_from_dataframe(\n",
        "    dataframe=valid_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "test_generator_ann = valid_test_datagen.flow_from_dataframe(\n",
        "    dataframe=test_df,\n",
        "    x_col='full_path',\n",
        "    y_col='labels',\n",
        "    target_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    class_mode='categorical',\n",
        "    shuffle=False\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1Cc5UYUzd_f1",
        "outputId": "caac2f84-b906-4cd7-9ce1-6edad9ef63f2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 13984 validated image filenames belonging to 5 classes.\n",
            "Found 832 validated image filenames belonging to 5 classes.\n",
            "Found 859 validated image filenames belonging to 5 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Build ANN\n",
        "from tensorflow.keras import layers, models\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "\n",
        "def build_ann(input_shape=(128,128,3), num_classes=5, dropout_rate=0.4):\n",
        "    model = models.Sequential([\n",
        "        layers.Flatten(input_shape=input_shape),   # 128*128*3 = 49152 input features\n",
        "\n",
        "        layers.Dense(512, activation='relu'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.Dropout(dropout_rate),\n",
        "\n",
        "        layers.Dense(256, activation='relu'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.Dropout(dropout_rate),\n",
        "\n",
        "        layers.Dense(128, activation='relu'),\n",
        "        layers.BatchNormalization(),\n",
        "        layers.Dropout(dropout_rate),\n",
        "\n",
        "        layers.Dense(64, activation='relu'),\n",
        "        layers.Dropout(dropout_rate),\n",
        "\n",
        "        layers.Dense(num_classes, activation='softmax')\n",
        "    ])\n",
        "    return model\n",
        "\n",
        "model_ann = build_ann()\n",
        "model_ann.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 648
        },
        "id": "GIRpWrlreHBo",
        "outputId": "6bd2f475-b1b8-479e-c9ea-9bd254f9135e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/keras/src/layers/reshaping/flatten.py:37: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
            "  super().__init__(**kwargs)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential_2\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_2\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m49152\u001b[0m)          │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_6 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │    \u001b[38;5;34m25,166,336\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_11          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │         \u001b[38;5;34m2,048\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_4 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_7 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m131,328\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_12          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m1,024\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_5 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_8 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_13          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │           \u001b[38;5;34m512\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_6 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_9 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │         \u001b[38;5;34m8,256\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_7 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_10 (\u001b[38;5;33mDense\u001b[0m)                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m)              │           \u001b[38;5;34m325\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ flatten_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">49152</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │    <span style=\"color: #00af00; text-decoration-color: #00af00\">25,166,336</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_11          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,048</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">131,328</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_12          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_13          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,256</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">325</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m25,342,725\u001b[0m (96.67 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">25,342,725</span> (96.67 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m25,340,933\u001b[0m (96.67 MB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">25,340,933</span> (96.67 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m1,792\u001b[0m (7.00 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,792</span> (7.00 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Compile ANN\n",
        "model_ann.compile(\n",
        "    optimizer=Adam(learning_rate=0.001),\n",
        "    loss='categorical_crossentropy',\n",
        "    metrics=['accuracy']\n",
        ")"
      ],
      "metadata": {
        "id": "e7HeYQA1eK0H"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Callbacks for ANN\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n",
        "\n",
        "early_stop_ann = EarlyStopping(monitor='val_loss', patience=6, restore_best_weights=True)\n",
        "checkpoint_ann = ModelCheckpoint('best_model_ann.keras', monitor='val_accuracy', save_best_only=True)\n",
        "reduce_lr_ann = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3, min_lr=1e-6)\n",
        "\n",
        "callbacks_ann = [early_stop_ann, checkpoint_ann, reduce_lr_ann]"
      ],
      "metadata": {
        "id": "qYNFZrWBeOY5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Train model\n",
        "EPOCHS_ANN = 15\n",
        "\n",
        "history_ann = model_ann.fit(\n",
        "    train_generator_ann,\n",
        "    steps_per_epoch=len(train_generator_ann),\n",
        "    validation_data=valid_generator_ann,\n",
        "    validation_steps=len(valid_generator_ann),\n",
        "    epochs=EPOCHS_ANN,\n",
        "    class_weight=class_weights,\n",
        "    callbacks=callbacks_ann\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IP2txiRveT0q",
        "outputId": "d98168f2-ad05-4bb5-b363-faaf6d9c2da0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m63s\u001b[0m 140ms/step - accuracy: 0.3006 - loss: 1.6562 - val_accuracy: 0.2488 - val_loss: 1.6138 - learning_rate: 0.0010\n",
            "Epoch 2/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 138ms/step - accuracy: 0.3475 - loss: 1.3495 - val_accuracy: 0.3534 - val_loss: 1.3513 - learning_rate: 0.0010\n",
            "Epoch 3/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 137ms/step - accuracy: 0.3640 - loss: 1.2796 - val_accuracy: 0.4038 - val_loss: 1.2833 - learning_rate: 0.0010\n",
            "Epoch 4/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m62s\u001b[0m 141ms/step - accuracy: 0.3772 - loss: 1.2565 - val_accuracy: 0.4279 - val_loss: 1.2471 - learning_rate: 0.0010\n",
            "Epoch 5/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 136ms/step - accuracy: 0.3874 - loss: 1.2338 - val_accuracy: 0.4038 - val_loss: 1.2772 - learning_rate: 0.0010\n",
            "Epoch 6/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m62s\u001b[0m 141ms/step - accuracy: 0.3992 - loss: 1.2198 - val_accuracy: 0.4519 - val_loss: 1.2332 - learning_rate: 0.0010\n",
            "Epoch 7/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 137ms/step - accuracy: 0.4091 - loss: 1.2045 - val_accuracy: 0.4411 - val_loss: 1.2724 - learning_rate: 0.0010\n",
            "Epoch 8/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 139ms/step - accuracy: 0.4066 - loss: 1.2115 - val_accuracy: 0.4279 - val_loss: 1.2504 - learning_rate: 0.0010\n",
            "Epoch 9/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m60s\u001b[0m 138ms/step - accuracy: 0.4118 - loss: 1.2073 - val_accuracy: 0.4375 - val_loss: 1.2937 - learning_rate: 0.0010\n",
            "Epoch 10/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 139ms/step - accuracy: 0.4163 - loss: 1.1793 - val_accuracy: 0.4267 - val_loss: 1.2621 - learning_rate: 5.0000e-04\n",
            "Epoch 11/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 140ms/step - accuracy: 0.4249 - loss: 1.1768 - val_accuracy: 0.4050 - val_loss: 1.3382 - learning_rate: 5.0000e-04\n",
            "Epoch 12/15\n",
            "\u001b[1m437/437\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m61s\u001b[0m 140ms/step - accuracy: 0.4331 - loss: 1.1815 - val_accuracy: 0.4411 - val_loss: 1.2378 - learning_rate: 5.0000e-04\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Accuracy and Loss curves\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "acc_ann = history_ann.history['accuracy']\n",
        "val_acc_ann = history_ann.history['val_accuracy']\n",
        "loss_ann = history_ann.history['loss']\n",
        "val_loss_ann = history_ann.history['val_loss']\n",
        "epochs_range_ann = range(1, len(acc_ann) + 1)\n",
        "\n",
        "plt.figure(figsize=(14, 5))\n",
        "\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(epochs_range_ann, acc_ann, label='Train Accuracy')\n",
        "plt.plot(epochs_range_ann, val_acc_ann, label='Validation Accuracy')\n",
        "plt.title('ANN - Accuracy Curve')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(epochs_range_ann, loss_ann, label='Train Loss')\n",
        "plt.plot(epochs_range_ann, val_loss_ann, label='Validation Loss')\n",
        "plt.title('ANN - Loss Curve')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "id": "uxwBNpypeVh6",
        "outputId": "5104e04c-d121-447b-9511-9a6f39a9010c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predict on test data\n",
        "import numpy as np\n",
        "\n",
        "test_generator_ann.reset()\n",
        "\n",
        "y_pred_probs_ann = model_ann.predict(test_generator_ann, steps=len(test_generator_ann), verbose=1)\n",
        "y_pred_ann = np.argmax(y_pred_probs_ann, axis=1)\n",
        "\n",
        "y_true_ann = test_generator_ann.classes\n",
        "y_true_ann = np.array(y_true_ann) # Convert to numpy array to use .shape\n",
        "\n",
        "class_labels = list(test_generator_ann.class_indices.keys())\n",
        "print(\"Class labels order:\", class_labels)\n",
        "print(\"Predicted shape:\", y_pred_ann.shape, \"True shape:\", y_true_ann.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ead3FhXQhfzG",
        "outputId": "71bea8df-26c7-4b82-c99a-430cf061cdfc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m27/27\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 59ms/step\n",
            "Class labels order: ['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n",
            "Predicted shape: (859,) True shape: (859,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Classification report\n",
        "from sklearn.metrics import classification_report, accuracy_score\n",
        "\n",
        "print(\"ANN Test Accuracy:\", accuracy_score(y_true_ann, y_pred_ann))\n",
        "print(\"\\nClassification Report (ANN):\\n\")\n",
        "print(classification_report(y_true_ann, y_pred_ann, target_names=class_labels, digits=4))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fTBBu7mIhrt1",
        "outputId": "9e3e0c98-4f7b-40e8-858a-e4b310d207e7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "ANN Test Accuracy: 0.43888242142025613\n",
            "\n",
            "Classification Report (ANN):\n",
            "\n",
            "                    precision    recall  f1-score   support\n",
            "\n",
            "frog_eye_leaf_spot     0.2507    0.6391    0.3602       133\n",
            "           healthy     0.5462    0.5793    0.5622       347\n",
            "    powdery_mildew     0.5714    0.4444    0.5000        36\n",
            "              rust     0.6588    0.6154    0.6364        91\n",
            "              scab     0.4872    0.0754    0.1306       252\n",
            "\n",
            "          accuracy                         0.4389       859\n",
            "         macro avg     0.5029    0.4707    0.4379       859\n",
            "      weighted avg     0.4961    0.4389    0.4096       859\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Confusion Matrix\n",
        "from sklearn.metrics import confusion_matrix\n",
        "import seaborn as sns\n",
        "\n",
        "cm_ann = confusion_matrix(y_true_ann, y_pred_ann)\n",
        "\n",
        "plt.figure(figsize=(8, 6))\n",
        "sns.heatmap(cm_ann, annot=True, fmt='d', cmap='Oranges',\n",
        "            xticklabels=class_labels, yticklabels=class_labels)\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('Actual')\n",
        "plt.title('ANN - Confusion Matrix')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "id": "ByvhY1LZhwnh",
        "outputId": "c4168d88-92c5-4115-da3f-c72f240e5290"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Model Comparison"
      ],
      "metadata": {
        "id": "2hAQfRakiQvS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n",
        "\n",
        "def get_metrics(y_true, y_pred, model_name):\n",
        "    return {\n",
        "        'Model': model_name,\n",
        "        'Accuracy': accuracy_score(y_true, y_pred),\n",
        "        'Precision (macro)': precision_score(y_true, y_pred, average='macro'),\n",
        "        'Recall (macro)': recall_score(y_true, y_pred, average='macro'),\n",
        "        'F1-score (macro)': f1_score(y_true, y_pred, average='macro'),\n",
        "        'Precision (weighted)': precision_score(y_true, y_pred, average='weighted'),\n",
        "        'Recall (weighted)': recall_score(y_true, y_pred, average='weighted'),\n",
        "        'F1-score (weighted)': f1_score(y_true, y_pred, average='weighted'),\n",
        "    }\n",
        "\n",
        "results = []\n",
        "results.append(get_metrics(y_true, y_pred, 'CNN Model 1'))\n",
        "results.append(get_metrics(y_true2, y_pred2, 'CNN Model 2'))\n",
        "results.append(get_metrics(y_true_ann, y_pred_ann, 'ANN'))\n",
        "\n",
        "comparison_df = pd.DataFrame(results)\n",
        "comparison_df = comparison_df.set_index('Model')\n",
        "print(comparison_df.round(4))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IUUyKF9LiOuS",
        "outputId": "edf5473a-fcd4-4bd5-d50d-54a38530cc0a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "             Accuracy  Precision (macro)  Recall (macro)  F1-score (macro)  \\\n",
            "Model                                                                        \n",
            "CNN Model 1    0.8754             0.9006          0.8709            0.8769   \n",
            "CNN Model 2    0.8976             0.9170          0.8678            0.8851   \n",
            "ANN            0.4389             0.5029          0.4707            0.4379   \n",
            "\n",
            "             Precision (weighted)  Recall (weighted)  F1-score (weighted)  \n",
            "Model                                                                      \n",
            "CNN Model 1                0.8906             0.8754               0.8700  \n",
            "CNN Model 2                0.9056             0.8976               0.8943  \n",
            "ANN                        0.4961             0.4389               0.4096  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Bar Chart\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "metrics_to_plot = ['Accuracy', 'Precision (macro)', 'Recall (macro)', 'F1-score (macro)']\n",
        "\n",
        "comparison_df[metrics_to_plot].plot(kind='bar', figsize=(10, 6))\n",
        "plt.title('Model Comparison: CNN v1 vs CNN v2 vs ANN')\n",
        "plt.ylabel('Score')\n",
        "plt.xticks(rotation=0)\n",
        "plt.ylim(0, 1)\n",
        "plt.legend(loc='lower right')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 607
        },
        "id": "f3OcUwConhx4",
        "outputId": "c9f23b07-612d-47f8-af8f-0ef5a00f03b8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Overlay validation curve\n",
        "plt.figure(figsize=(14, 5))\n",
        "\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(history.history['val_accuracy'], label='CNN Model 1')\n",
        "plt.plot(history2.history['val_accuracy'], label='CNN Model 2')\n",
        "plt.plot(history_ann.history['val_accuracy'], label='ANN')\n",
        "plt.title('Validation Accuracy Comparison')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(history.history['val_loss'], label='CNN Model 1')\n",
        "plt.plot(history2.history['val_loss'], label='CNN Model 2')\n",
        "plt.plot(history_ann.history['val_loss'], label='ANN')\n",
        "plt.title('Validation Loss Comparison')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "id": "ZDIFxKdtnmvp",
        "outputId": "c147ab73-c119-42e5-d7e7-16d58f719fb6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ],
  "metadata": {
    "accelerator": "TPU",
    "colab": {
      "gpuType": "V6E1",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}