{ "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": "markdown", "source": [ "# Base Model Code : Step 1 - Load Libraries" ], "metadata": { "id": "uStPmcljWwS-" } }, { "cell_type": "code", "source": [ "import os\n", "\n", "import tensorflow as tf\n", "\n", "from tensorflow.keras import layers, models\n", "\n", "import matplotlib.pyplot as plt\n", "\n", "\n", "base_dir = r\"/content/drive/MyDrive/PlantPathology_Split\"\n" ], "metadata": { "id": "gHbR_5fxV5Bf" }, "execution_count": 4, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Step 2 - Load the datasets" ], "metadata": { "id": "lgCRA7xnXBou" } }, { "cell_type": "code", "source": [ "IMG_SIZE = (512, 512)\n", "\n", "BATCH_SIZE = 32\n", "\n", "\n", "\n", "train_ds = tf.keras.utils.image_dataset_from_directory(\n", "\n", " r\"/content/drive/MyDrive/PlantPathology_Split/train\",\n", "\n", " image_size=IMG_SIZE,\n", "\n", " batch_size=BATCH_SIZE,\n", "\n", " label_mode=\"int\"\n", "\n", ")\n", "\n", "\n", "\n", "valid_ds = tf.keras.utils.image_dataset_from_directory(\n", "\n", " r\"/content/drive/MyDrive/PlantPathology_Split/valid\",\n", "\n", " image_size=IMG_SIZE,\n", "\n", " batch_size=BATCH_SIZE,\n", "\n", " label_mode=\"int\"\n", "\n", ")\n", "\n", "\n", "\n", "test_ds = tf.keras.utils.image_dataset_from_directory(\n", "\n", " r\"/content/drive/MyDrive/PlantPathology_Split/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", "\n", "\n", "class_names = train_ds.class_names\n", "\n", "\n", "\n", "print(\"Classes:\")\n", "\n", "print(class_names)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 0 }, "id": "XNTPct-iWAQG", "outputId": "b5469edf-5f36-4eb0-930b-36358db44524" }, "execution_count": 5, "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", "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" ] } ] }, { "cell_type": "markdown", "source": [ "# Step 3 - Optimise data loading, using a TensorFlow tool" ], "metadata": { "id": "P5waXGavXKKq" } }, { "cell_type": "code", "source": [ "AUTOTUNE = tf.data.AUTOTUNE\n", "\n", "\n", "\n", "train_ds = train_ds.prefetch(AUTOTUNE)\n", "\n", "valid_ds = valid_ds.prefetch(AUTOTUNE)\n", "\n", "test_ds = test_ds.prefetch(AUTOTUNE)\n" ], "metadata": { "id": "ut0uYNFfWIbN" }, "execution_count": 6, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Step 4 - Build a basic CNN" ], "metadata": { "id": "kq-1TVwCXS2z" } }, { "cell_type": "code", "source": [ "num_classes = len(class_names)\n", "\n", "\n", "\n", "model = models.Sequential([\n", "\n", "\n", "\n", " layers.Rescaling(1./255, input_shape=(512, 512, 3)),\n", "\n", "\n", "\n", " layers.Conv2D(32, 3, activation='relu'),\n", "\n", " layers.MaxPooling2D(),\n", "\n", "\n", "\n", " layers.Conv2D(64, 3, activation='relu'),\n", "\n", " layers.MaxPooling2D(),\n", "\n", "\n", "\n", " layers.Flatten(),\n", "\n", "\n", "\n", " layers.Dense(128, activation='relu'),\n", "\n", " layers.Dropout(0.5),\n", "\n", "\n", "\n", " layers.Dense(num_classes, activation='softmax')\n", "\n", "])\n", "\n", "\n", "\n", "model.summary()\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 472 }, "id": "zy09nyXuWRWy", "outputId": "d3e03eee-5ec5-4ec3-9d87-78482a2655da" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/keras/src/layers/preprocessing/data_layer.py:95: 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\"\u001b[0m\n" ], "text/html": [ "
Model: \"sequential\"\n",
              "
\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", "│ rescaling (\u001b[38;5;33mRescaling\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m255\u001b[0m, \u001b[38;5;34m255\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;34m253\u001b[0m, \u001b[38;5;34m253\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m64\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;34m1016064\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;34m128\u001b[0m) │ \u001b[38;5;34m130,056,320\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout (\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_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m) │ \u001b[38;5;34m1,548\u001b[0m │\n", "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" ], "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ rescaling (Rescaling)           │ (None, 512, 512, 3)    │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d (Conv2D)                 │ (None, 510, 510, 32)   │           896 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (MaxPooling2D)    │ (None, 255, 255, 32)   │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (Conv2D)               │ (None, 253, 253, 64)   │        18,496 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (MaxPooling2D)  │ (None, 126, 126, 64)   │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (Flatten)               │ (None, 1016064)        │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (Dense)                   │ (None, 128)            │   130,056,320 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (Dropout)               │ (None, 128)            │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (Dense)                 │ (None, 12)             │         1,548 │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m130,077,260\u001b[0m (496.21 MB)\n" ], "text/html": [ "
 Total params: 130,077,260 (496.21 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m130,077,260\u001b[0m (496.21 MB)\n" ], "text/html": [ "
 Trainable params: 130,077,260 (496.21 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
              "
\n" ] }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "# Step 5 - Compile the model" ], "metadata": { "id": "NWgHyv8mXb4U" } }, { "cell_type": "code", "source": [ "model.compile(\n", "\n", " optimizer='adam',\n", "\n", " loss='sparse_categorical_crossentropy',\n", "\n", " metrics=['accuracy']\n", "\n", ")" ], "metadata": { "id": "kXhJPqCZWWy-" }, "execution_count": 8, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Step 6 - Train the model" ], "metadata": { "id": "OkSJPywDXiaE" } }, { "cell_type": "code", "source": [ "history = model.fit(\n", "\n", " train_ds,\n", "\n", " validation_data=valid_ds,\n", "\n", " epochs=3\n", "\n", ")\n", "\n", "\n", "\n", "\n", "\n", "plt.figure(figsize=(12,5))\n", "\n", "# Check the results\n", "\n", "\n", "\n", "# Accuracy\n", "\n", "plt.subplot(1,2,1)\n", "\n", "plt.plot(history.history['accuracy'])\n", "\n", "plt.plot(history.history['val_accuracy'])\n", "\n", "plt.title(\"Model Accuracy\")\n", "\n", "plt.xlabel(\"Epoch\")\n", "\n", "plt.ylabel(\"Accuracy\")\n", "\n", "plt.legend(['Train','Validation'])\n", "\n", "\n", "\n", "# Loss\n", "\n", "plt.subplot(1,2,2)\n", "\n", "plt.plot(history.history['loss'])\n", "\n", "plt.plot(history.history['val_loss'])\n", "\n", "plt.title(\"Model Loss\")\n", "\n", "plt.xlabel(\"Epoch\")\n", "\n", "plt.ylabel(\"Loss\")\n", "\n", "plt.legend(['Train','Validation'])\n", "\n", "\n", "\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 418 }, "id": "KPmdQyLZWc5S", "outputId": "a7ca2b1b-b6c2-4e64-c0a2-a01770bfd6a6" }, "execution_count": 9, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/3\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1829s\u001b[0m 7s/step - accuracy: 0.3066 - loss: 2.5860 - val_accuracy: 0.3453 - val_loss: 1.7105\n", "Epoch 2/3\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m66s\u001b[0m 244ms/step - accuracy: 0.3810 - loss: 1.7139 - val_accuracy: 0.4033 - val_loss: 1.6090\n", "Epoch 3/3\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m68s\u001b[0m 248ms/step - accuracy: 0.4584 - loss: 1.5287 - val_accuracy: 0.4280 - val_loss: 1.5853\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "# Step 7 - Evaluate on the test set" ], "metadata": { "id": "9NpmEpKjXwz_" } }, { "cell_type": "code", "source": [ "test_loss, test_accuracy = model.evaluate(test_ds)\n", "\n", "\n", "\n", "print(f\"\\nTest Accuracy: {test_accuracy:.4f}\")\n", "\n", "print(f\"Test Loss: {test_loss:.4f}\")\n", "\n", "model.summary()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 502 }, "id": "3r2JW8PeWndT", "outputId": "6ac29a94-fdb3-47c8-b9b0-67100651b72e" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m347s\u001b[0m 6s/step - accuracy: 0.4090 - loss: 1.5723\n", "\n", "Test Accuracy: 0.4090\n", "Test Loss: 1.5723\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1mModel: \"sequential\"\u001b[0m\n" ], "text/html": [ "
Model: \"sequential\"\n",
              "
\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", "│ rescaling (\u001b[38;5;33mRescaling\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m255\u001b[0m, \u001b[38;5;34m255\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;34m253\u001b[0m, \u001b[38;5;34m253\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m64\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;34m1016064\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;34m128\u001b[0m) │ \u001b[38;5;34m130,056,320\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout (\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_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m) │ \u001b[38;5;34m1,548\u001b[0m │\n", "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" ], "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ rescaling (Rescaling)           │ (None, 512, 512, 3)    │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d (Conv2D)                 │ (None, 510, 510, 32)   │           896 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (MaxPooling2D)    │ (None, 255, 255, 32)   │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (Conv2D)               │ (None, 253, 253, 64)   │        18,496 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (MaxPooling2D)  │ (None, 126, 126, 64)   │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (Flatten)               │ (None, 1016064)        │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (Dense)                   │ (None, 128)            │   130,056,320 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (Dropout)               │ (None, 128)            │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (Dense)                 │ (None, 12)             │         1,548 │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m390,231,782\u001b[0m (1.45 GB)\n" ], "text/html": [ "
 Total params: 390,231,782 (1.45 GB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m130,077,260\u001b[0m (496.21 MB)\n" ], "text/html": [ "
 Trainable params: 130,077,260 (496.21 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m260,154,522\u001b[0m (992.41 MB)\n" ], "text/html": [ "
 Optimizer params: 260,154,522 (992.41 MB)\n",
              "
\n" ] }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "\n", "# Change Model Code STEP 1: Import Core Python Libraries\n" ], "metadata": { "id": "QhMEY-Xx4MEF" } }, { "cell_type": "code", "execution_count": 11, "metadata": { "id": "5I9sUSMXD676" }, "outputs": [], "source": [ "import os\n", "import numpy as np\n", "import tensorflow as tf\n", "from tensorflow.keras import layers\n", "import matplotlib.pyplot as plt\n", "from sklearn.metrics import classification_report, confusion_matrix\n", "import seaborn as sns" ] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 2: Define Root Folder Paths" ], "metadata": { "id": "5B1u2USf4iNq" } }, { "cell_type": "code", "source": [ "BASE_DIR = r\"/content/drive/MyDrive/PlantPathology_Split\"\n", "TRAIN_DIR = os.path.join(BASE_DIR, \"train\")\n", "VALID_DIR = os.path.join(BASE_DIR, \"valid\")\n", "TEST_DIR = os.path.join(BASE_DIR, \"test\")" ], "metadata": { "id": "b0WuEE4WD_iu" }, "execution_count": 12, "outputs": [] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 3: Define Image Dimensions and Batch Size" ], "metadata": { "id": "Sz1VgHvk4q5a" } }, { "cell_type": "code", "source": [ "IMG_HEIGHT = 224\n", "IMG_WIDTH = 224\n", "BATCH_SIZE = 32" ], "metadata": { "id": "U6jLnDY0ECIS" }, "execution_count": 13, "outputs": [] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 4: Load Datasets in RGB\n" ], "metadata": { "id": "mlVwf-Nj4yuE" } }, { "cell_type": "code", "source": [ "train_ds = tf.keras.utils.image_dataset_from_directory(\n", " TRAIN_DIR,\n", " image_size=(IMG_HEIGHT, IMG_WIDTH),\n", " batch_size=BATCH_SIZE,\n", " label_mode=\"int\",\n", " color_mode=\"rgb\"\n", ")\n", "\n", "valid_ds = tf.keras.utils.image_dataset_from_directory(\n", " VALID_DIR,\n", " image_size=(IMG_HEIGHT, IMG_WIDTH),\n", " batch_size=BATCH_SIZE,\n", " label_mode=\"int\",\n", " color_mode=\"rgb\"\n", ")\n", "\n", "test_ds = tf.keras.utils.image_dataset_from_directory(\n", " TEST_DIR,\n", " image_size=(IMG_HEIGHT, IMG_WIDTH),\n", " batch_size=BATCH_SIZE,\n", " label_mode=\"int\",\n", " color_mode=\"rgb\",\n", " shuffle=False\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 0 }, "id": "gRFtZ96bEFYg", "outputId": "a8e96da5-dd26-4fd7-fac1-17d7a3ad3141" }, "execution_count": 14, "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" ] } ] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 5: Retrieve and Display Folder Class Names\n" ], "metadata": { "id": "jONVRLlq44gi" } }, { "cell_type": "code", "source": [ "class_names = train_ds.class_names\n", "num_classes = len(class_names)\n", "print(\"\\nDetected Classes:\", class_names)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 0 }, "id": "1FxdKS1GEIbK", "outputId": "437586a8-144f-4589-97fb-f4192eab2563" }, "execution_count": 15, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Detected Classes: ['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" ] } ] }, { "cell_type": "markdown", "source": [ "\n", "# STEPS 6: Configure Performance Prefetching\n", "\n" ], "metadata": { "id": "E_kdMmkc4-Mg" } }, { "cell_type": "code", "source": [ "AUTOTUNE = tf.data.AUTOTUNE\n", "train_ds = train_ds.prefetch(buffer_size=AUTOTUNE)\n", "valid_ds = valid_ds.prefetch(buffer_size=AUTOTUNE)\n", "test_ds = test_ds.prefetch(buffer_size=AUTOTUNE)" ], "metadata": { "id": "a5pGKCKCEK6S" }, "execution_count": 16, "outputs": [] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 7: Define Data Augmentation & Base Model\n" ], "metadata": { "id": "1zZP0gKz5Kp6" } }, { "cell_type": "code", "source": [ "data_augmentation = tf.keras.Sequential([\n", " layers.RandomFlip(\"horizontal_and_vertical\"),\n", " layers.RandomRotation(0.2),\n", " layers.RandomZoom(0.2),\n", " layers.RandomContrast(0.1),\n", "])\n", "\n", "\n", "base_model = tf.keras.applications.MobileNetV2(\n", " input_shape=(IMG_HEIGHT, IMG_WIDTH, 3),\n", " include_top=False,\n", " weights='imagenet'\n", ")\n", "base_model.trainable = False" ], "metadata": { "id": "uJ2Skvy-EORi", "colab": { "base_uri": "https://localhost:8080/", "height": 0 }, "outputId": "38552682-53f6-4266-da36-7cfa0c779212" }, "execution_count": 17, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.0_224_no_top.h5\n", "\u001b[1m9406464/9406464\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n" ] } ] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 8: Build the Network (Functional API)\n" ], "metadata": { "id": "H0g0KCNY5RDq" } }, { "cell_type": "code", "source": [ "inputs = layers.Input(shape=(IMG_HEIGHT, IMG_WIDTH, 3))\n", "\n", "\n", "x = data_augmentation(inputs)\n", "\n", "\n", "x = tf.keras.applications.mobilenet_v2.preprocess_input(x)\n", "\n", "\n", "x = base_model(x, training=False)\n", "\n", "\n", "x = layers.GlobalAveragePooling2D()(x)\n", "\n", "\n", "x = layers.Dense(256, activation='relu')(x)\n", "x = layers.BatchNormalization()(x)\n", "x = layers.Dropout(0.4)(x)\n", "\n", "\n", "outputs = layers.Dense(num_classes, activation='softmax')(x)\n", "\n", "model = tf.keras.Model(inputs=inputs, outputs=outputs)" ], "metadata": { "id": "rxNIQSGJEU4U" }, "execution_count": 18, "outputs": [] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 9: Define Smart Training Callbacks\n" ], "metadata": { "id": "qFuNjUYB5YPV" } }, { "cell_type": "code", "source": [ "early_stopping = tf.keras.callbacks.EarlyStopping(\n", " monitor='val_loss',\n", " patience=4,\n", " restore_best_weights=True,\n", " verbose=1\n", ")\n", "\n", "\n", "reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(\n", " monitor='val_loss',\n", " factor=0.2,\n", " patience=2,\n", " min_lr=1e-6,\n", " verbose=1\n", ")\n", "\n", "\n", "checkpoint = tf.keras.callbacks.ModelCheckpoint(\n", " filepath=\"best_plant_pathology_model.keras\",\n", " monitor=\"val_accuracy\",\n", " save_best_only=True,\n", " mode=\"max\",\n", " verbose=1\n", ")\n", "\n", "callbacks_list = [early_stopping, reduce_lr, checkpoint]" ], "metadata": { "id": "qS7MWXUPEZpx" }, "execution_count": 19, "outputs": [] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 10: Compile the Model\n" ], "metadata": { "id": "8kp9EkBW5eYn" } }, { "cell_type": "code", "source": [ "model.compile(\n", " optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),\n", " loss='sparse_categorical_crossentropy',\n", " metrics=['accuracy']\n", ")\n", "\n", "print(\"\\n--- MobileNetV2 Expanded Model Summary ---\")\n", "model.summary()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 532 }, "id": "iqSahq_wEc9E", "outputId": "5088a525-30d0-4df1-a198-27bf39feab84" }, "execution_count": 20, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "--- MobileNetV2 Expanded Model Summary ---\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1mModel: \"functional_2\"\u001b[0m\n" ], "text/html": [ "
Model: \"functional_2\"\n",
              "
\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_2 (\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_1 (\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", "│ true_divide (\u001b[38;5;33mTrueDivide\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", "│ subtract (\u001b[38;5;33mSubtract\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", "│ mobilenetv2_1.00_224 │ (\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;34m2,257,984\u001b[0m │\n", "│ (\u001b[38;5;33mFunctional\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", "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m327,936\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ batch_normalization │ (\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_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_3 (\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": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_2 (InputLayer)      │ (None, 224, 224, 3)    │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential_1 (Sequential)       │ (None, 224, 224, 3)    │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ true_divide (TrueDivide)        │ (None, 224, 224, 3)    │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ subtract (Subtract)             │ (None, 224, 224, 3)    │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ mobilenetv2_1.00_224            │ (None, 7, 7, 1280)     │     2,257,984 │\n",
              "│ (Functional)                    │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d        │ (None, 1280)           │             0 │\n",
              "│ (GlobalAveragePooling2D)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (Dense)                 │ (None, 256)            │       327,936 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (None, 256)            │         1,024 │\n",
              "│ (BatchNormalization)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (Dropout)             │ (None, 256)            │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (Dense)                 │ (None, 12)             │         3,084 │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m2,590,028\u001b[0m (9.88 MB)\n" ], "text/html": [ "
 Total params: 2,590,028 (9.88 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m331,532\u001b[0m (1.26 MB)\n" ], "text/html": [ "
 Trainable params: 331,532 (1.26 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m2,258,496\u001b[0m (8.62 MB)\n" ], "text/html": [ "
 Non-trainable params: 2,258,496 (8.62 MB)\n",
              "
\n" ] }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 11: Train the Model with Callbacks\n" ], "metadata": { "id": "Tuc0AU6W5mhY" } }, { "cell_type": "code", "source": [ "print(\"\\n--- Starting Model Training ---\")\n", "history = model.fit(\n", " train_ds,\n", " validation_data=valid_ds,\n", " epochs=15,\n", " callbacks=callbacks_list\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 0 }, "id": "8da7cY_-EfrL", "outputId": "6cc5f9c6-1876-47f4-b5af-21e93484b11c" }, "execution_count": 21, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "--- Starting Model Training ---\n", "Epoch 1/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 143ms/step - accuracy: 0.5142 - loss: 1.7230\n", "Epoch 1: val_accuracy improved from None to 0.66756, saving model to best_plant_pathology_model.keras\n", "\n", "Epoch 1: finished saving model to best_plant_pathology_model.keras\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m63s\u001b[0m 186ms/step - accuracy: 0.5966 - loss: 1.3801 - val_accuracy: 0.6676 - val_loss: 1.0549 - learning_rate: 0.0010\n", "Epoch 2/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 148ms/step - accuracy: 0.6520 - loss: 1.0722\n", "Epoch 2: val_accuracy improved from 0.66756 to 0.71214, saving model to best_plant_pathology_model.keras\n", "\n", "Epoch 2: finished saving model to best_plant_pathology_model.keras\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m75s\u001b[0m 188ms/step - accuracy: 0.6601 - loss: 1.0503 - val_accuracy: 0.7121 - val_loss: 0.8978 - learning_rate: 0.0010\n", "Epoch 3/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 142ms/step - accuracy: 0.6749 - loss: 1.0182\n", "Epoch 3: val_accuracy did not improve from 0.71214\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m48s\u001b[0m 175ms/step - accuracy: 0.6761 - loss: 0.9971 - val_accuracy: 0.6778 - val_loss: 0.9781 - learning_rate: 0.0010\n", "Epoch 4/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 150ms/step - accuracy: 0.6878 - loss: 0.9675\n", "Epoch 4: ReduceLROnPlateau reducing learning rate to 0.00020000000949949026.\n", "\n", "Epoch 4: val_accuracy did not improve from 0.71214\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m48s\u001b[0m 177ms/step - accuracy: 0.6916 - loss: 0.9443 - val_accuracy: 0.6778 - val_loss: 0.9790 - learning_rate: 0.0010\n", "Epoch 5/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 149ms/step - accuracy: 0.7011 - loss: 0.9095\n", "Epoch 5: val_accuracy improved from 0.71214 to 0.72664, saving model to best_plant_pathology_model.keras\n", "\n", "Epoch 5: finished saving model to best_plant_pathology_model.keras\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m50s\u001b[0m 185ms/step - accuracy: 0.7028 - loss: 0.9032 - val_accuracy: 0.7266 - val_loss: 0.8785 - learning_rate: 2.0000e-04\n", "Epoch 6/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 147ms/step - accuracy: 0.7089 - loss: 0.8891\n", "Epoch 6: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m49s\u001b[0m 179ms/step - accuracy: 0.7085 - loss: 0.8792 - val_accuracy: 0.7127 - val_loss: 0.8873 - learning_rate: 2.0000e-04\n", "Epoch 7/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 153ms/step - accuracy: 0.7071 - loss: 0.8922\n", "Epoch 7: ReduceLROnPlateau reducing learning rate to 4.0000001899898055e-05.\n", "\n", "Epoch 7: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m50s\u001b[0m 184ms/step - accuracy: 0.7136 - loss: 0.8711 - val_accuracy: 0.7116 - val_loss: 0.8829 - learning_rate: 2.0000e-04\n", "Epoch 8/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 150ms/step - accuracy: 0.7138 - loss: 0.8761\n", "Epoch 8: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m50s\u001b[0m 185ms/step - accuracy: 0.7160 - loss: 0.8602 - val_accuracy: 0.7186 - val_loss: 0.8673 - learning_rate: 4.0000e-05\n", "Epoch 9/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 150ms/step - accuracy: 0.7097 - loss: 0.8789\n", "Epoch 9: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m49s\u001b[0m 179ms/step - accuracy: 0.7137 - loss: 0.8692 - val_accuracy: 0.7213 - val_loss: 0.8642 - learning_rate: 4.0000e-05\n", "Epoch 10/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 153ms/step - accuracy: 0.7136 - loss: 0.8618\n", "Epoch 10: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 180ms/step - accuracy: 0.7138 - loss: 0.8546 - val_accuracy: 0.7148 - val_loss: 0.8642 - learning_rate: 4.0000e-05\n", "Epoch 11/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 153ms/step - accuracy: 0.7175 - loss: 0.8711\n", "Epoch 11: ReduceLROnPlateau reducing learning rate to 8.000000525498762e-06.\n", "\n", "Epoch 11: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m52s\u001b[0m 191ms/step - accuracy: 0.7199 - loss: 0.8568 - val_accuracy: 0.7154 - val_loss: 0.8667 - learning_rate: 4.0000e-05\n", "Epoch 12/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 152ms/step - accuracy: 0.7157 - loss: 0.8732\n", "Epoch 12: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 180ms/step - accuracy: 0.7166 - loss: 0.8571 - val_accuracy: 0.7191 - val_loss: 0.8624 - learning_rate: 8.0000e-06\n", "Epoch 13/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 154ms/step - accuracy: 0.7165 - loss: 0.8651\n", "Epoch 13: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 182ms/step - accuracy: 0.7183 - loss: 0.8491 - val_accuracy: 0.7186 - val_loss: 0.8674 - learning_rate: 8.0000e-06\n", "Epoch 14/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 152ms/step - accuracy: 0.7220 - loss: 0.8531\n", "Epoch 14: ReduceLROnPlateau reducing learning rate to 1.6000001778593287e-06.\n", "\n", "Epoch 14: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m52s\u001b[0m 190ms/step - accuracy: 0.7184 - loss: 0.8475 - val_accuracy: 0.7175 - val_loss: 0.8668 - learning_rate: 8.0000e-06\n", "Epoch 15/15\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 152ms/step - accuracy: 0.7162 - loss: 0.8633\n", "Epoch 15: val_accuracy did not improve from 0.72664\n", "\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 185ms/step - accuracy: 0.7190 - loss: 0.8496 - val_accuracy: 0.7170 - val_loss: 0.8662 - learning_rate: 1.6000e-06\n", "Restoring model weights from the end of the best epoch: 12.\n" ] } ] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 12: Visualize Training History\n" ], "metadata": { "id": "PxS3AnIE5tNr" } }, { "cell_type": "code", "source": [ "plt.figure(figsize=(12, 5))\n", "\n", "plt.subplot(1, 2, 1)\n", "plt.plot(history.history['accuracy'], label='Train Accuracy')\n", "plt.plot(history.history['val_accuracy'], label='Val Accuracy')\n", "plt.title(\"Accuracy Trends\")\n", "plt.xlabel(\"Epoch\")\n", "plt.ylabel(\"Accuracy\")\n", "plt.legend()\n", "\n", "plt.subplot(1, 2, 2)\n", "plt.plot(history.history['loss'], label='Train Loss')\n", "plt.plot(history.history['val_loss'], label='Val Loss')\n", "plt.title(\"Loss Trends\")\n", "plt.xlabel(\"Epoch\")\n", "plt.ylabel(\"Loss\")\n", "plt.legend()\n", "\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 294 }, "id": "XAErlv8HEi1H", "outputId": "31d39a14-e6d5-49b2-84be-ff601e582f42" }, "execution_count": 22, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "\n", "# STEP 13: Comprehensive Evaluation (Confusion Matrix & Report)\n" ], "metadata": { "id": "ZgjLWG2F51Dz" } }, { "cell_type": "code", "source": [ "print(\"\\n--- Evaluating Model on Test Set ---\")\n", "test_loss, test_accuracy = model.evaluate(test_ds)\n", "print(f\"Test Accuracy: {test_accuracy:.4f}\")\n", "\n", "\n", "y_true = np.concatenate([y for x, y in test_ds], axis=0)\n", "y_pred_probs = model.predict(test_ds)\n", "y_pred = np.argmax(y_pred_probs, axis=1)\n", "\n", "\n", "print(\"\\n--- Classification Report ---\")\n", "print(classification_report(y_true, y_pred, target_names=class_names))\n", "\n", "\n", "cm = confusion_matrix(y_true, y_pred)\n", "plt.figure(figsize=(8, 6))\n", "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n", "plt.title('Plant Pathology Confusion Matrix')\n", "plt.ylabel('True Class')\n", "plt.xlabel('Predicted Class')\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "McF-YV76Emkz", "outputId": "271d47a0-a567-4619-dc32-477a99489e9e" }, "execution_count": 23, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "--- Evaluating Model on Test Set ---\n", "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 163ms/step - accuracy: 0.7279 - loss: 0.8393\n", "Test Accuracy: 0.7279\n", "\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 139ms/step\n", "\n", "--- Classification Report ---\n", " precision recall f1-score support\n", "\n", " complex 0.46 0.49 0.48 160\n", " frog_eye_leaf_spot 0.62 0.88 0.72 310\n", " frog_eye_leaf_spot complex 0.00 0.00 0.00 16\n", " healthy 0.87 0.86 0.86 445\n", " powdery_mildew 0.77 0.85 0.81 126\n", " powdery_mildew complex 0.00 0.00 0.00 8\n", " rust 0.83 0.61 0.70 186\n", " rust complex 1.00 0.22 0.36 9\n", " rust frog_eye_leaf_spot 0.00 0.00 0.00 13\n", " scab 0.80 0.78 0.79 500\n", " scab frog_eye_leaf_spot 0.25 0.15 0.19 73\n", "scab frog_eye_leaf_spot complex 0.00 0.00 0.00 17\n", "\n", " accuracy 0.73 1863\n", " macro avg 0.47 0.40 0.41 1863\n", " weighted avg 0.71 0.73 0.71 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" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] } ] }