{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "import matplotlib.pyplot as plt\n",
        "import zipfile\n",
        "import os\n",
        "\n",
        "from tensorflow.keras import layers\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras.applications import EfficientNetB0"
      ],
      "metadata": {
        "id": "1Jcsk7bwvvPB"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "for root, dirs, files in os.walk(\"/content\"):\n",
        "    for file in files:\n",
        "        if file.endswith(\".zip\"):\n",
        "            print(os.path.join(root, file))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S2Am_ncdFvwE",
        "outputId": "d2746c9c-581c-4158-b5ce-4f894ba1813a"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/PlantPathology_Split.zip\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import zipfile\n",
        "import os\n",
        "\n",
        "zip_file = \"/content/PlantPathology_Split.zip\"\n",
        "extract_path = \"/content/PlantPathology_Split\"\n",
        "\n",
        "with zipfile.ZipFile(zip_file, \"r\") as zip_ref:\n",
        "    zip_ref.extractall(extract_path)\n",
        "\n",
        "print(\"Extraction completed!\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4CswI5BtGEcL",
        "outputId": "83f4f265-df43-47ee-a05e-f98219a86932"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extraction completed!\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "base_dir = None\n",
        "\n",
        "for root, dirs, files in os.walk(extract_path):\n",
        "\n",
        "    if \"train\" in dirs and \"valid\" in dirs and \"test\" in dirs:\n",
        "        base_dir = root\n",
        "        break\n",
        "\n",
        "print(\"Dataset Path:\")\n",
        "print(base_dir)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YXFq2y_4GLGL",
        "outputId": "49c4ace0-9a90-4541-a161-60fbe744c83e"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Dataset Path:\n",
            "/content/PlantPathology_Split/PlantPathology_Split\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "IMG_SIZE = (224,224)\n",
        "\n",
        "BATCH_SIZE = 32\n",
        "\n",
        "train_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "\n",
        "    os.path.join(base_dir,\"train\"),\n",
        "\n",
        "    image_size=IMG_SIZE,\n",
        "\n",
        "    batch_size=BATCH_SIZE,\n",
        "\n",
        "    label_mode=\"int\"\n",
        "\n",
        ")\n",
        "\n",
        "valid_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "\n",
        "    os.path.join(base_dir,\"valid\"),\n",
        "\n",
        "    image_size=IMG_SIZE,\n",
        "\n",
        "    batch_size=BATCH_SIZE,\n",
        "\n",
        "    label_mode=\"int\"\n",
        "\n",
        ")\n",
        "\n",
        "test_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "\n",
        "    os.path.join(base_dir,\"test\"),\n",
        "\n",
        "    image_size=IMG_SIZE,\n",
        "\n",
        "    batch_size=BATCH_SIZE,\n",
        "\n",
        "    label_mode=\"int\",\n",
        "\n",
        "    shuffle=False\n",
        "\n",
        ")\n",
        "\n",
        "class_names = train_ds.class_names\n",
        "\n",
        "print(class_names)\n",
        "\n",
        "print(\"Number of Classes =\",len(class_names))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TUq88fqfGYAs",
        "outputId": "9dedeebf-a138-47dd-b05c-d57bc76d7eee"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 8691 files belonging to 12 classes.\n",
            "Found 1862 files belonging to 12 classes.\n",
            "Found 1863 files belonging to 12 classes.\n",
            "['complex', 'frog_eye_leaf_spot', 'frog_eye_leaf_spot complex', 'healthy', 'powdery_mildew', 'powdery_mildew complex', 'rust', 'rust complex', 'rust frog_eye_leaf_spot', 'scab', 'scab frog_eye_leaf_spot', 'scab frog_eye_leaf_spot complex']\n",
            "Number of Classes = 12\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "AUTOTUNE = tf.data.AUTOTUNE\n",
        "\n",
        "train_ds = train_ds.cache().shuffle(1000).prefetch(AUTOTUNE)\n",
        "\n",
        "valid_ds = valid_ds.cache().prefetch(AUTOTUNE)\n",
        "\n",
        "test_ds = test_ds.cache().prefetch(AUTOTUNE)"
      ],
      "metadata": {
        "id": "K7uXWkErGa0x"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data_augmentation = tf.keras.Sequential([\n",
        "\n",
        "    layers.RandomFlip(\"horizontal\"),\n",
        "\n",
        "    layers.RandomRotation(0.2),\n",
        "\n",
        "    layers.RandomZoom(0.2),\n",
        "\n",
        "    layers.RandomContrast(0.2),\n",
        "\n",
        "    layers.RandomTranslation(0.1,0.1),\n",
        "\n",
        "])"
      ],
      "metadata": {
        "id": "H_I8vMhgGdsc"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "base_model = EfficientNetB0(\n",
        "\n",
        "    include_top=False,\n",
        "\n",
        "    weights=\"imagenet\",\n",
        "\n",
        "    input_shape=(224,224,3)\n",
        "\n",
        ")\n",
        "\n",
        "base_model.trainable = False\n",
        "\n",
        "print(\"EfficientNetB0 Loaded Successfully\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "o_qzIIdlGnEx",
        "outputId": "9b1c18ca-9623-4117-d311-fe1b78ac0ce3"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/keras-applications/efficientnetb0_notop.h5\n",
            "\u001b[1m16705208/16705208\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n",
            "EfficientNetB0 Loaded Successfully\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "inputs = tf.keras.Input(shape=(224,224,3))\n",
        "\n",
        "x = data_augmentation(inputs)\n",
        "\n",
        "x = tf.keras.applications.efficientnet.preprocess_input(x)\n",
        "\n",
        "x = base_model(x, training=False)\n",
        "\n",
        "x = layers.GlobalAveragePooling2D()(x)\n",
        "\n",
        "x = layers.BatchNormalization()(x)\n",
        "\n",
        "x = layers.Dense(512, activation=\"relu\")(x)\n",
        "\n",
        "x = layers.Dropout(0.5)(x)\n",
        "\n",
        "x = layers.Dense(256, activation=\"relu\")(x)\n",
        "\n",
        "x = layers.Dropout(0.3)(x)\n",
        "\n",
        "outputs = layers.Dense(len(class_names), activation=\"softmax\")(x)\n",
        "\n",
        "model = Model(inputs, outputs)\n",
        "\n",
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 481
        },
        "id": "APCfzCWAGoqz",
        "outputId": "b254ba04-29b0-4c35-9d3c-ace2909f93e4"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"functional_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: \"functional_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",
              "│ input_layer_1 (\u001b[38;5;33mInputLayer\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential (\u001b[38;5;33mSequential\u001b[0m)         │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ efficientnetb0 (\u001b[38;5;33mFunctional\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m1280\u001b[0m)     │     \u001b[38;5;34m4,049,571\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1280\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n",
              "│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1280\u001b[0m)           │         \u001b[38;5;34m5,120\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │       \u001b[38;5;34m655,872\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (\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_1 (\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",
              "│ dropout_1 (\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_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m)             │         \u001b[38;5;34m3,084\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",
              "│ input_layer_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Sequential</span>)         │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">224</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ efficientnetb0 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">7</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">7</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1280</span>)     │     <span style=\"color: #00af00; text-decoration-color: #00af00\">4,049,571</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1280</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1280</span>)           │         <span style=\"color: #00af00; text-decoration-color: #00af00\">5,120</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</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\">512</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">655,872</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\">512</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\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">131,328</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\">256</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\">12</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">3,084</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,844,975\u001b[0m (18.48 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\">4,844,975</span> (18.48 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m792,844\u001b[0m (3.02 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\">792,844</span> (3.02 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m4,052,131\u001b[0m (15.46 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\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,052,131</span> (15.46 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(\n",
        "\n",
        "    optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001),\n",
        "\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "\n",
        "    metrics=[\"accuracy\"]\n",
        "\n",
        ")"
      ],
      "metadata": {
        "id": "p9P6y6rJGsvX"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "early_stop = tf.keras.callbacks.EarlyStopping(\n",
        "\n",
        "    monitor=\"val_loss\",\n",
        "\n",
        "    patience=5,\n",
        "\n",
        "    restore_best_weights=True\n",
        "\n",
        ")\n",
        "\n",
        "reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(\n",
        "\n",
        "    monitor=\"val_loss\",\n",
        "\n",
        "    factor=0.2,\n",
        "\n",
        "    patience=2,\n",
        "\n",
        "    min_lr=1e-6,\n",
        "\n",
        "    verbose=1\n",
        "\n",
        ")"
      ],
      "metadata": {
        "id": "DpQsjG4IGwwT"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(\n",
        "\n",
        "    train_ds,\n",
        "\n",
        "    validation_data=valid_ds,\n",
        "\n",
        "    epochs=15,\n",
        "\n",
        "    callbacks=[early_stop, reduce_lr]\n",
        "\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pRvwSI6vGy1s",
        "outputId": "d13e744b-ebbd-4b03-f7a1-d95a824e5d90"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 105ms/step - accuracy: 0.3494 - loss: 2.0277 - val_accuracy: 0.5924 - val_loss: 1.3830 - learning_rate: 1.0000e-04\n",
            "Epoch 2/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m44s\u001b[0m 86ms/step - accuracy: 0.4923 - loss: 1.5625 - val_accuracy: 0.6407 - val_loss: 1.1651 - learning_rate: 1.0000e-04\n",
            "Epoch 3/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 86ms/step - accuracy: 0.5315 - loss: 1.4315 - val_accuracy: 0.6504 - val_loss: 1.1039 - learning_rate: 1.0000e-04\n",
            "Epoch 4/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 87ms/step - accuracy: 0.5568 - loss: 1.3558 - val_accuracy: 0.6735 - val_loss: 1.0573 - learning_rate: 1.0000e-04\n",
            "Epoch 5/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 87ms/step - accuracy: 0.5860 - loss: 1.2825 - val_accuracy: 0.6890 - val_loss: 1.0190 - learning_rate: 1.0000e-04\n",
            "Epoch 6/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 88ms/step - accuracy: 0.5959 - loss: 1.2334 - val_accuracy: 0.6858 - val_loss: 1.0092 - learning_rate: 1.0000e-04\n",
            "Epoch 7/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 89ms/step - accuracy: 0.6034 - loss: 1.2135 - val_accuracy: 0.6917 - val_loss: 0.9943 - learning_rate: 1.0000e-04\n",
            "Epoch 8/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 89ms/step - accuracy: 0.6219 - loss: 1.1493 - val_accuracy: 0.7009 - val_loss: 0.9729 - learning_rate: 1.0000e-04\n",
            "Epoch 9/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 90ms/step - accuracy: 0.6254 - loss: 1.1449 - val_accuracy: 0.6998 - val_loss: 0.9600 - learning_rate: 1.0000e-04\n",
            "Epoch 10/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 90ms/step - accuracy: 0.6286 - loss: 1.1222 - val_accuracy: 0.7105 - val_loss: 0.9478 - learning_rate: 1.0000e-04\n",
            "Epoch 11/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 90ms/step - accuracy: 0.6372 - loss: 1.1068 - val_accuracy: 0.7137 - val_loss: 0.9377 - learning_rate: 1.0000e-04\n",
            "Epoch 12/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 90ms/step - accuracy: 0.6455 - loss: 1.0843 - val_accuracy: 0.7052 - val_loss: 0.9494 - learning_rate: 1.0000e-04\n",
            "Epoch 13/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m25s\u001b[0m 91ms/step - accuracy: 0.6515 - loss: 1.0595 - val_accuracy: 0.7164 - val_loss: 0.9370 - learning_rate: 1.0000e-04\n",
            "Epoch 14/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m25s\u001b[0m 90ms/step - accuracy: 0.6550 - loss: 1.0374 - val_accuracy: 0.7164 - val_loss: 0.9318 - learning_rate: 1.0000e-04\n",
            "Epoch 15/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 90ms/step - accuracy: 0.6548 - loss: 1.0377 - val_accuracy: 0.7105 - val_loss: 0.9375 - learning_rate: 1.0000e-04\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Unfreeze the base model\n",
        "base_model.trainable = True\n",
        "\n",
        "# Freeze all layers except the last 30\n",
        "for layer in base_model.layers[:-30]:\n",
        "    layer.trainable = False\n",
        "\n",
        "print(\"Fine-tuning last 30 layers...\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "juMCM7PVG1IT",
        "outputId": "c9d93738-0eda-49c6-f3e5-81caa05093a2"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fine-tuning last 30 layers...\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(\n",
        "    optimizer=tf.keras.optimizers.Adam(learning_rate=1e-5),\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")"
      ],
      "metadata": {
        "id": "8T92U1KlI3Tm"
      },
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(\n",
        "    train_ds,\n",
        "    validation_data=valid_ds,\n",
        "    epochs=15,\n",
        "    callbacks=[early_stop, reduce_lr]\n",
        ")\n",
        "\n",
        "test_loss, test_accuracy = model.evaluate(test_ds)\n",
        "\n",
        "print(\"Test Accuracy:\", test_accuracy)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7ks5LKMBI4zo",
        "outputId": "48a47dd6-254b-402f-e27c-504f11567ec0"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 102ms/step - accuracy: 0.5361 - loss: 1.3714 - val_accuracy: 0.6595 - val_loss: 1.0833 - learning_rate: 1.0000e-06\n",
            "Epoch 2/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 101ms/step - accuracy: 0.5479 - loss: 1.3586 - val_accuracy: 0.6638 - val_loss: 1.0749 - learning_rate: 1.0000e-06\n",
            "Epoch 3/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 102ms/step - accuracy: 0.5487 - loss: 1.3371 - val_accuracy: 0.6660 - val_loss: 1.0628 - learning_rate: 1.0000e-06\n",
            "Epoch 4/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 103ms/step - accuracy: 0.5623 - loss: 1.3283 - val_accuracy: 0.6713 - val_loss: 1.0572 - learning_rate: 1.0000e-06\n",
            "Epoch 5/15\n",
            "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 103ms/step - accuracy: 0.5517 - loss: 1.3408 - val_accuracy: 0.6719 - val_loss: 1.0522 - learning_rate: 1.0000e-06\n",
            "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 83ms/step - accuracy: 0.6667 - loss: 1.0574\n",
            "Test Accuracy: 0.6666666865348816\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.figure(figsize=(14,5))\n",
        "\n",
        "# Accuracy\n",
        "plt.subplot(1,2,1)\n",
        "plt.plot(history.history['accuracy'], marker='o')\n",
        "plt.plot(history.history['val_accuracy'], marker='o')\n",
        "plt.title(\"Model Accuracy\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.legend([\"Training Accuracy\",\"Validation Accuracy\"])\n",
        "\n",
        "# Loss\n",
        "plt.subplot(1,2,2)\n",
        "plt.plot(history.history['loss'], marker='o')\n",
        "plt.plot(history.history['val_loss'], marker='o')\n",
        "plt.title(\"Model Loss\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Loss\")\n",
        "plt.legend([\"Training Loss\",\"Validation Loss\"])\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 304
        },
        "id": "LbRQm6sTI6X_",
        "outputId": "e3d7ac30-37a0-4278-a2d5-6d7ff4d46028"
      },
      "execution_count": 21,
      "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": [
        "import numpy as np\n",
        "\n",
        "y_true = np.concatenate([y for x, y in test_ds], axis=0)\n",
        "\n",
        "predictions = model.predict(test_ds)\n",
        "\n",
        "y_pred = np.argmax(predictions, axis=1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HdWvYCBHOWHs",
        "outputId": "9f314a61-6a3d-4dd4-801e-0ac107fa27d5"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 102ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import classification_report\n",
        "\n",
        "print(classification_report(\n",
        "    y_true,\n",
        "    y_pred,\n",
        "    target_names=class_names\n",
        "))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vSONP-P-OaiY",
        "outputId": "fa6dd126-aaf9-4d31-b41d-57a03b9368b5"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "                                 precision    recall  f1-score   support\n",
            "\n",
            "                        complex       0.33      0.20      0.25       160\n",
            "             frog_eye_leaf_spot       0.56      0.77      0.65       310\n",
            "     frog_eye_leaf_spot complex       0.00      0.00      0.00        16\n",
            "                        healthy       0.79      0.80      0.80       445\n",
            "                 powdery_mildew       0.83      0.80      0.81       126\n",
            "         powdery_mildew complex       0.00      0.00      0.00         8\n",
            "                           rust       0.60      0.74      0.67       186\n",
            "                   rust complex       0.00      0.00      0.00         9\n",
            "        rust frog_eye_leaf_spot       0.00      0.00      0.00        13\n",
            "                           scab       0.72      0.73      0.73       500\n",
            "        scab frog_eye_leaf_spot       0.26      0.12      0.17        73\n",
            "scab frog_eye_leaf_spot complex       0.00      0.00      0.00        17\n",
            "\n",
            "                       accuracy                           0.67      1863\n",
            "                      macro avg       0.34      0.35      0.34      1863\n",
            "                   weighted avg       0.63      0.67      0.64      1863\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
            "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
            "  _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import confusion_matrix\n",
        "import seaborn as sns\n",
        "\n",
        "cm = confusion_matrix(y_true, y_pred)\n",
        "\n",
        "plt.figure(figsize=(10,8))\n",
        "\n",
        "sns.heatmap(\n",
        "    cm,\n",
        "    annot=True,\n",
        "    fmt='d',\n",
        "    cmap='Blues',\n",
        "    xticklabels=class_names,\n",
        "    yticklabels=class_names\n",
        ")\n",
        "\n",
        "plt.xlabel(\"Predicted\")\n",
        "plt.ylabel(\"Actual\")\n",
        "plt.title(\"Confusion Matrix\")\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 666
        },
        "id": "bmUrs03gOfl_",
        "outputId": "abe20085-6782-40c4-85d9-76c10b9b45db"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.save(\"Plant_Disease_EfficientNetB0.keras\")\n",
        "\n",
        "print(\"Model Saved Successfully!\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Y7CvkD2dOoI2",
        "outputId": "66e3d60d-ef49-410d-c36f-cfaf3413a19e"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model Saved Successfully!\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "history_df = pd.DataFrame(history.history)\n",
        "\n",
        "history_df.to_csv(\"training_history.csv\", index=False)\n",
        "\n",
        "print(history_df.head())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4k1RtpO_Ouyk",
        "outputId": "3703b7a7-85dc-4938-c354-beacfbee77cd"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "   accuracy      loss  val_accuracy  val_loss  learning_rate\n",
            "0  0.536072  1.371436      0.659506  1.083323   1.000000e-06\n",
            "1  0.547923  1.358584      0.663802  1.074943   1.000000e-06\n",
            "2  0.548729  1.337133      0.665951  1.062753   1.000000e-06\n",
            "3  0.562306  1.328254      0.671321  1.057189   1.000000e-06\n",
            "4  0.551720  1.340816      0.671858  1.052245   1.000000e-06\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "j9NZ_0rsOx70"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}