{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "sM2hV4Ddhl1h"
},
"outputs": [],
"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"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "MYHzBXtZjNtx",
"outputId": "2b9f4739-bfc8-4b0b-cba2-b6b29fb7af2d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/content/PlantPathology_Split.zip\n"
]
}
],
"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))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "4bXZIwW8jbiP",
"outputId": "b2ccb07a-6431-4672-b792-8003aa179186"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Removing existing directory: /content/PlantPathology_Split\n",
"Extracting /content/PlantPathology_Split.zip to /content/PlantPathology_Split...\n",
"Extraction completed!\n"
]
}
],
"source": [
"import zipfile\n",
"import os\n",
"import shutil # Import shutil for rmtree\n",
"\n",
"zip_file = \"/content/PlantPathology_Split.zip\"\n",
"extract_path = \"/content/PlantPathology_Split\"\n",
"\n",
"# Ensure clean extraction: remove existing directory if it exists\n",
"if os.path.exists(extract_path):\n",
" print(f\"Removing existing directory: {extract_path}\")\n",
" shutil.rmtree(extract_path)\n",
"\n",
"print(f\"Extracting {zip_file} to {extract_path}...\")\n",
"with zipfile.ZipFile(zip_file, \"r\") as zip_ref:\n",
" zip_ref.extractall(extract_path)\n",
"\n",
"print(\"Extraction completed!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "XbVmdI-1jblt",
"outputId": "7fe63f48-2403-4a7a-d408-2e6a24e3e621"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset Path:\n",
"/content/PlantPathology_Split/PlantPathology_Split\n"
]
}
],
"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)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "OLYsQ-qsjboF",
"outputId": "6fca283d-b84a-43e7-9471-946cff159e64"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"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"
]
}
],
"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))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cxZdkbODjbqE"
},
"outputs": [],
"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)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "B1BuWxE6jbr4"
},
"outputs": [],
"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",
"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "m9aosgkxjbuI",
"outputId": "6acda64e-ada6-4154-bdaf-306f093fc6b5"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"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"
]
}
],
"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\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 481
},
"id": "iuVHVjQXjbvu",
"outputId": "fa9f8fd0-914b-4b6e-ab79-a6ed7322615c"
},
"outputs": [
{
"data": {
"text/html": [
"Model: \"functional_1\"\n",
"\n"
],
"text/plain": [
"\u001b[1mModel: \"functional_1\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ input_layer_1 (InputLayer) │ (None, 224, 224, 3) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ sequential (Sequential) │ (None, 224, 224, 3) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ efficientnetb0 (Functional) │ (None, 7, 7, 1280) │ 4,049,571 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ global_average_pooling2d │ (None, 1280) │ 0 │\n",
"│ (GlobalAveragePooling2D) │ │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ batch_normalization │ (None, 1280) │ 5,120 │\n",
"│ (BatchNormalization) │ │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (Dense) │ (None, 512) │ 655,872 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout (Dropout) │ (None, 512) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_1 (Dense) │ (None, 256) │ 131,328 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dropout_1 (Dropout) │ (None, 256) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_2 (Dense) │ (None, 12) │ 3,084 │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"\n"
],
"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"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Total params: 4,844,975 (18.48 MB)\n",
"\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,844,975\u001b[0m (18.48 MB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Trainable params: 792,844 (3.02 MB)\n",
"\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m792,844\u001b[0m (3.02 MB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Non-trainable params: 4,052,131 (15.46 MB)\n",
"\n"
],
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m4,052,131\u001b[0m (15.46 MB)\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"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()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZiU6SpyFjbyE"
},
"outputs": [],
"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",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "HJI_kHW2jb4H"
},
"outputs": [],
"source": [
"early_stop = tf.keras.callbacks.EarlyStopping(\n",
" monitor=\"val_loss\",\n",
" patience=5,\n",
" restore_best_weights=True,\n",
" verbose=1\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",
"checkpoint = tf.keras.callbacks.ModelCheckpoint(\n",
" \"best_model.keras\",\n",
" monitor=\"val_accuracy\",\n",
" save_best_only=True,\n",
" verbose=1\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true,
"base_uri": "https://localhost:8080/"
},
"id": "_cgKdQoNjb7H",
"outputId": "329ff8ed-74a9-4f03-ee75-9c17925084a5"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 73ms/step - accuracy: 0.2911 - loss: 2.3016\n",
"Epoch 1: val_accuracy improved from None to 0.58163, saving model to best_model.keras\n",
"\n",
"Epoch 1: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 114ms/step - accuracy: 0.3667 - loss: 1.9936 - val_accuracy: 0.5816 - val_loss: 1.4466 - learning_rate: 1.0000e-04\n",
"Epoch 2/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 75ms/step - accuracy: 0.4825 - loss: 1.6084\n",
"Epoch 2: val_accuracy improved from 0.58163 to 0.62621, saving model to best_model.keras\n",
"\n",
"Epoch 2: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m25s\u001b[0m 93ms/step - accuracy: 0.5016 - loss: 1.5437 - val_accuracy: 0.6262 - val_loss: 1.1855 - learning_rate: 1.0000e-04\n",
"Epoch 3/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 76ms/step - accuracy: 0.5315 - loss: 1.4412\n",
"Epoch 3: val_accuracy improved from 0.62621 to 0.65145, saving model to best_model.keras\n",
"\n",
"Epoch 3: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 95ms/step - accuracy: 0.5391 - loss: 1.4199 - val_accuracy: 0.6515 - val_loss: 1.1275 - learning_rate: 1.0000e-04\n",
"Epoch 4/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 78ms/step - accuracy: 0.5614 - loss: 1.3369\n",
"Epoch 4: val_accuracy improved from 0.65145 to 0.66917, saving model to best_model.keras\n",
"\n",
"Epoch 4: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 98ms/step - accuracy: 0.5616 - loss: 1.3378 - val_accuracy: 0.6692 - val_loss: 1.0858 - learning_rate: 1.0000e-04\n",
"Epoch 5/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.5878 - loss: 1.2845\n",
"Epoch 5: val_accuracy did not improve from 0.66917\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 101ms/step - accuracy: 0.5893 - loss: 1.2685 - val_accuracy: 0.6681 - val_loss: 1.0512 - learning_rate: 1.0000e-04\n",
"Epoch 6/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step - accuracy: 0.6086 - loss: 1.2098\n",
"Epoch 6: val_accuracy improved from 0.66917 to 0.67132, saving model to best_model.keras\n",
"\n",
"Epoch 6: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6055 - loss: 1.2184 - val_accuracy: 0.6713 - val_loss: 1.0349 - learning_rate: 1.0000e-04\n",
"Epoch 7/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 79ms/step - accuracy: 0.6291 - loss: 1.1686\n",
"Epoch 7: val_accuracy improved from 0.67132 to 0.67830, saving model to best_model.keras\n",
"\n",
"Epoch 7: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 99ms/step - accuracy: 0.6232 - loss: 1.1713 - val_accuracy: 0.6783 - val_loss: 1.0476 - learning_rate: 1.0000e-04\n",
"Epoch 8/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step - accuracy: 0.6340 - loss: 1.1347\n",
"Epoch 8: val_accuracy improved from 0.67830 to 0.68314, saving model to best_model.keras\n",
"\n",
"Epoch 8: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6255 - loss: 1.1571 - val_accuracy: 0.6831 - val_loss: 1.0210 - learning_rate: 1.0000e-04\n",
"Epoch 9/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step - accuracy: 0.6340 - loss: 1.1304\n",
"Epoch 9: val_accuracy improved from 0.68314 to 0.69334, saving model to best_model.keras\n",
"\n",
"Epoch 9: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6298 - loss: 1.1390 - val_accuracy: 0.6933 - val_loss: 0.9965 - learning_rate: 1.0000e-04\n",
"Epoch 10/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step - accuracy: 0.6207 - loss: 1.1535\n",
"Epoch 10: val_accuracy did not improve from 0.69334\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 97ms/step - accuracy: 0.6249 - loss: 1.1289 - val_accuracy: 0.6880 - val_loss: 0.9941 - learning_rate: 1.0000e-04\n",
"Epoch 11/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step - accuracy: 0.6298 - loss: 1.1284\n",
"Epoch 11: val_accuracy improved from 0.69334 to 0.69603, saving model to best_model.keras\n",
"\n",
"Epoch 11: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6370 - loss: 1.1109 - val_accuracy: 0.6960 - val_loss: 0.9751 - learning_rate: 1.0000e-04\n",
"Epoch 12/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6340 - loss: 1.1135\n",
"Epoch 12: val_accuracy improved from 0.69603 to 0.69764, saving model to best_model.keras\n",
"\n",
"Epoch 12: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 99ms/step - accuracy: 0.6427 - loss: 1.0857 - val_accuracy: 0.6976 - val_loss: 0.9807 - learning_rate: 1.0000e-04\n",
"Epoch 13/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6642 - loss: 1.0257\n",
"Epoch 13: val_accuracy improved from 0.69764 to 0.70032, saving model to best_model.keras\n",
"\n",
"Epoch 13: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6519 - loss: 1.0550 - val_accuracy: 0.7003 - val_loss: 0.9446 - learning_rate: 1.0000e-04\n",
"Epoch 14/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6662 - loss: 1.0283\n",
"Epoch 14: val_accuracy improved from 0.70032 to 0.71053, saving model to best_model.keras\n",
"\n",
"Epoch 14: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6630 - loss: 1.0384 - val_accuracy: 0.7105 - val_loss: 0.9271 - learning_rate: 1.0000e-04\n",
"Epoch 15/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6593 - loss: 1.0279\n",
"Epoch 15: val_accuracy did not improve from 0.71053\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 97ms/step - accuracy: 0.6608 - loss: 1.0292 - val_accuracy: 0.7073 - val_loss: 0.9279 - learning_rate: 1.0000e-04\n",
"Epoch 16/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6576 - loss: 1.0409\n",
"Epoch 16: val_accuracy did not improve from 0.71053\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 98ms/step - accuracy: 0.6600 - loss: 1.0201 - val_accuracy: 0.7100 - val_loss: 0.9206 - learning_rate: 1.0000e-04\n",
"Epoch 17/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6619 - loss: 1.0220\n",
"Epoch 17: val_accuracy did not improve from 0.71053\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 97ms/step - accuracy: 0.6608 - loss: 1.0166 - val_accuracy: 0.7073 - val_loss: 0.9228 - learning_rate: 1.0000e-04\n",
"Epoch 18/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6776 - loss: 1.0285\n",
"Epoch 18: val_accuracy improved from 0.71053 to 0.71912, saving model to best_model.keras\n",
"\n",
"Epoch 18: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6743 - loss: 1.0160 - val_accuracy: 0.7191 - val_loss: 0.9142 - learning_rate: 1.0000e-04\n",
"Epoch 19/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6759 - loss: 0.9972\n",
"Epoch 19: val_accuracy improved from 0.71912 to 0.72127, saving model to best_model.keras\n",
"\n",
"Epoch 19: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6806 - loss: 0.9872 - val_accuracy: 0.7213 - val_loss: 0.9007 - learning_rate: 1.0000e-04\n",
"Epoch 20/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 81ms/step - accuracy: 0.6715 - loss: 0.9785\n",
"Epoch 20: val_accuracy improved from 0.72127 to 0.72556, saving model to best_model.keras\n",
"\n",
"Epoch 20: finished saving model to best_model.keras\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 100ms/step - accuracy: 0.6754 - loss: 0.9798 - val_accuracy: 0.7256 - val_loss: 0.8879 - learning_rate: 1.0000e-04\n",
"Restoring model weights from the end of the best epoch: 20.\n"
]
}
],
"source": [
"history1 = model.fit(\n",
" train_ds,\n",
" validation_data=valid_ds,\n",
" epochs=20,\n",
" callbacks=[\n",
" early_stop,\n",
" reduce_lr,\n",
" checkpoint\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "PfYCZqsJjb9e",
"outputId": "6fae85cf-8a31-4627-e909-bdcc9baedb8d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Fine-tuning last 20 layers...\n"
]
}
],
"source": [
"base_model.trainable = True\n",
"\n",
"for layer in base_model.layers[:-20]:\n",
" layer.trainable = False\n",
"\n",
"print(\"Fine-tuning last 20 layers...\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "dYLshMtHjb_H"
},
"outputs": [],
"source": [
"model.compile(\n",
" optimizer=tf.keras.optimizers.Adam(\n",
" learning_rate=1e-5\n",
" ),\n",
" loss=\"sparse_categorical_crossentropy\",\n",
" metrics=[\"accuracy\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "OlZ--l-YjcBl",
"outputId": "c4bd5d77-aca8-49a6-84d0-2ed859f811f2"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 91ms/step - accuracy: 0.5151 - loss: 1.4342\n",
"Epoch 1: val_accuracy did not improve from 0.72556\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m46s\u001b[0m 118ms/step - accuracy: 0.5308 - loss: 1.3935 - val_accuracy: 0.6649 - val_loss: 1.0540 - learning_rate: 1.0000e-05\n",
"Epoch 2/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 92ms/step - accuracy: 0.5713 - loss: 1.2765\n",
"Epoch 2: ReduceLROnPlateau reducing learning rate to 1.9999999494757505e-06.\n",
"\n",
"Epoch 2: val_accuracy did not improve from 0.72556\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 108ms/step - accuracy: 0.5758 - loss: 1.2822 - val_accuracy: 0.6643 - val_loss: 1.0483 - learning_rate: 1.0000e-05\n",
"Epoch 3/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 89ms/step - accuracy: 0.6040 - loss: 1.2209\n",
"Epoch 3: val_accuracy did not improve from 0.72556\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 105ms/step - accuracy: 0.5952 - loss: 1.2366 - val_accuracy: 0.6633 - val_loss: 1.0396 - learning_rate: 2.0000e-06\n",
"Epoch 4/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - accuracy: 0.5927 - loss: 1.2436\n",
"Epoch 4: ReduceLROnPlateau reducing learning rate to 1e-06.\n",
"\n",
"Epoch 4: val_accuracy did not improve from 0.72556\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 106ms/step - accuracy: 0.5942 - loss: 1.2304 - val_accuracy: 0.6686 - val_loss: 1.0353 - learning_rate: 2.0000e-06\n",
"Epoch 5/20\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 90ms/step - accuracy: 0.5910 - loss: 1.2362\n",
"Epoch 5: val_accuracy did not improve from 0.72556\n",
"\u001b[1m272/272\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 107ms/step - accuracy: 0.5934 - loss: 1.2272 - val_accuracy: 0.6697 - val_loss: 1.0321 - learning_rate: 1.0000e-06\n",
"Epoch 5: early stopping\n",
"Restoring model weights from the end of the best epoch: 1.\n",
"\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 87ms/step - accuracy: 0.6785 - loss: 1.0163\n",
"Test Accuracy: 0.678475558757782\n"
]
}
],
"source": [
"history2 = model.fit(\n",
" train_ds,\n",
" validation_data=valid_ds,\n",
" epochs=20,\n",
" callbacks=[\n",
" early_stop,\n",
" reduce_lr,\n",
" checkpoint\n",
" ]\n",
")\n",
"\n",
"test_loss, test_accuracy = model.evaluate(test_ds)\n",
"\n",
"print(\"Test Accuracy:\", test_accuracy)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "6ef18c97",
"outputId": "4e8748df-b6e6-4eb1-c5df-a86e5ec45798"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m59/59\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 109ms/step\n"
]
}
],
"source": [
"import numpy as np\n",
"from sklearn.metrics import confusion_matrix\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# Get predictions on the test dataset\n",
"predictions = model.predict(test_ds)\n",
"predicted_classes = np.argmax(predictions, axis=1)\n",
"\n",
"# Get true labels from the test dataset\n",
"true_classes = np.concatenate([y for x, y in test_ds], axis=0)\n",
"\n",
"# Compute the confusion matrix\n",
"cm = confusion_matrix(true_classes, predicted_classes)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "4a11f268",
"outputId": "d24a5c0b-91a3-4668-e594-35af5e3b5c2f"
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Plot the confusion matrix as a heatmap\n",
"plt.figure(figsize=(12, 10))\n",
"sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n",
" xticklabels=class_names, yticklabels=class_names)\n",
"plt.xlabel('Predicted Label')\n",
"plt.ylabel('True Label')\n",
"plt.title('Confusion Matrix Heatmap')\n",
"plt.xticks(rotation=90)\n",
"plt.yticks(rotation=0)\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "c58110c1"
},
"source": [
"### Confusion Matrix for the First 5 Classes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "25b76666"
},
"outputs": [],
"source": [
"import numpy as np\n",
"from sklearn.metrics import confusion_matrix\n",
"import tensorflow as tf # Added for dataset creation\n",
"import os # Added for dataset path\n",
"\n",
"# --- Ensure core variables for dataset and model are available ---\n",
"# Assume these are constants from earlier cells if not in globals\n",
"# Fallback values are hardcoded from the notebook's execution history to increase robustness\n",
"IMG_SIZE = globals().get('IMG_SIZE', (224, 224))\n",
"BATCH_SIZE = globals().get('BATCH_SIZE', 32)\n",
"base_dir = globals().get('base_dir', '/content/PlantPathology_Split/PlantPathology_Split')\n",
"\n",
"# Ensure train_ds and test_ds are available. Recreate if missing.\n",
"if 'train_ds' not in globals() or 'test_ds' not in globals():\n",
" print(\"Re-creating train_ds and test_ds as they were not found in the current scope.\")\n",
" train_ds = tf.keras.utils.image_dataset_from_directory(\n",
" os.path.join(base_dir, \"train\"),\n",
" image_size=IMG_SIZE,\n",
" batch_size=BATCH_SIZE,\n",
" label_mode=\"int\"\n",
" )\n",
" test_ds = tf.keras.utils.image_dataset_from_directory(\n",
" os.path.join(base_dir, \"test\"),\n",
" image_size=IMG_SIZE,\n",
" batch_size=BATCH_SIZE,\n",
" label_mode=\"int\",\n",
" shuffle=False\n",
" )\n",
"\n",
"# Ensure class_names is available. Re-derive from train_ds if missing.\n",
"if 'class_names' not in globals():\n",
" print(\"Re-defining class_names from train_ds.\")\n",
" class_names = train_ds.class_names\n",
"\n",
"# Ensure true_classes and predicted_classes are available. Recalculate if missing.\n",
"if 'true_classes' not in globals() or 'predicted_classes' not in globals():\n",
" if 'model' in globals():\n",
" print(\"Re-calculating predictions as they were not found in the current scope.\")\n",
" predictions = globals()['model'].predict(test_ds)\n",
" predicted_classes = np.argmax(predictions, axis=1)\n",
" true_classes = np.concatenate([y for x, y in test_ds], axis=0)\n",
" else:\n",
" raise NameError(\"Model is not defined. Please ensure model training cells (e.g., _cgKdQoNjb7H or OlZ--l-YjcBl) have been executed to define 'model'.\")\n",
"\n",
"# --- Original logic for 5-class heatmap ---\n",
"# Select the first 5 class names\n",
"first_5_class_names = class_names[:5]\n",
"\n",
"# Get the indices of the first 5 classes\n",
"first_5_class_indices = list(range(len(first_5_class_names)))\n",
"\n",
"# Filter true and predicted classes to only include the first 5 classes\n",
"filtered_true_classes = []\n",
"filtered_predicted_classes = []\n",
"\n",
"for i in range(len(true_classes)):\n",
" if true_classes[i] in first_5_class_indices:\n",
" filtered_true_classes.append(true_classes[i])\n",
" filtered_predicted_classes.append(predicted_classes[i])\n",
"\n",
"# Convert to numpy arrays\n",
"filtered_true_classes = np.array(filtered_true_classes)\n",
"filtered_predicted_classes = np.array(filtered_predicted_classes)\n",
"\n",
"# Compute the confusion matrix for the first 5 classes\n",
"cm_5_classes = confusion_matrix(filtered_true_classes, filtered_predicted_classes, labels=first_5_class_indices)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "0db9a0d3",
"outputId": "be234f16-68f5-4b90-c1e2-1a9b7dccfc3f"
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"# Plot the confusion matrix for the first 5 classes\n",
"plt.figure(figsize=(10, 8))\n",
"sns.heatmap(cm_5_classes, annot=True, fmt='d', cmap='Blues',\n",
" xticklabels=first_5_class_names, yticklabels=first_5_class_names)\n",
"plt.xlabel('Predicted Label')\n",
"plt.ylabel('True Label')\n",
"plt.title('Confusion Matrix Heatmap for First 5 Classes')\n",
"plt.xticks(rotation=45, ha='right')\n",
"plt.yticks(rotation=0)\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "NwvH_0jmjcDN",
"outputId": "6f61fb59-4c51-4ad5-a3dd-fea8bb1e8e85"
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(14,5))\n",
"\n",
"plt.subplot(1,2,1)\n",
"plt.plot(history1.history[\"accuracy\"])\n",
"plt.plot(history1.history[\"val_accuracy\"])\n",
"plt.title(\"Accuracy\")\n",
"plt.xlabel(\"Epoch\")\n",
"plt.ylabel(\"Accuracy\")\n",
"plt.legend([\"Train\",\"Validation\"])\n",
"\n",
"plt.subplot(1,2,2)\n",
"plt.plot(history1.history[\"loss\"])\n",
"plt.plot(history1.history[\"val_loss\"])\n",
"plt.title(\"Loss\")\n",
"plt.xlabel(\"Epoch\")\n",
"plt.ylabel(\"Loss\")\n",
"plt.legend([\"Train\",\"Validation\"])\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "nJt5ZV3njcFL",
"outputId": "78c76de1-8ef6-47a7-89a0-629bdfff3970"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model Saved Successfully!\n"
]
}
],
"source": [
"model.save(\"Plant_Disease_EfficientNetB0_Final.keras\")\n",
"\n",
"print(\"Model Saved Successfully!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "dwCrDbg0jcHr"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "peLRcbI0jcJW"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "IMCCHtZ_jcLB"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "TDkTvvaMjcM9"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "fXLi5k-5jcPi"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "dHtr2p1LjcSt"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "mas9cifpjcYu"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "Wl0NVv_Zjcct"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "KlEsd8a_jcep"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "7ZtEVxSFjcg7"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "gWCT9iomjcis"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "dGLAIEiFjclC"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "pAwbTicejcmy"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "ooS-Yd08jcon"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "XKN3jpGFjcqX"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "FFHyLqjNjctw"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "fEhHDRdCjcv7"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "xqkVW-oKjczJ"
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true
},
"id": "r8AkXg-9jc2K"
},
"outputs": [],
"source": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}