Update app.py

app.py

@@ -1,59 +1,36 @@
+import gradio as gr
+import matplotlib.pyplot as plt
+import numpy as np
 import os
-import zipfile
-import gdown
-import pathlib
+import PIL
 import tensorflow as tf
 from tensorflow import keras
 from tensorflow.keras import layers
 from tensorflow.keras.models import Sequential
-import matplotlib.pyplot as plt
-import gradio as gr
-import numpy as np
+from PIL import Image
+import gdown
+import zipfile
+import pathlib
 
-# Define the Google Drive shareable link
+# Download and extract dataset
 gdrive_url = 'https://drive.google.com/file/d/1HjHYlQyRz5oWt8kehkt1TiOGRRlKFsv8/view?usp=drive_link'
-
-# Extract the file ID from the URL
 file_id = gdrive_url.split('/d/')[1].split('/view')[0]
 direct_download_url = f'https://drive.google.com/uc?id={file_id}'
-
-# Define the local filename to save the ZIP file
 local_zip_file = 'file.zip'
-
-# Download the ZIP file
 gdown.download(direct_download_url, local_zip_file, quiet=False)
-
-# Directory to extract files
 extracted_path = 'extracted_files'
-
-# Verify if the downloaded file is a ZIP file and extract it
 try:
     with zipfile.ZipFile(local_zip_file, 'r') as zip_ref:
         zip_ref.extractall(extracted_path)
     print("Extraction successful!")
 except zipfile.BadZipFile:
     print("Error: The downloaded file is not a valid ZIP file.")
-
-# Optionally, you can delete the ZIP file after extraction
 os.remove(local_zip_file)
+data_dir = pathlib.Path(extracted_path) / 'Pest_Dataset'
 
-# Convert the extracted directory path to a pathlib.Path object
-data_dir = pathlib.Path('extracted_files/Pest_Dataset')
-
-# Verify the directory structure
-for root, dirs, files in os.walk(extracted_path):
-    level = root.replace(extracted_path, '').count(os.sep)
-    indent = ' ' * 4 * (level)
-    print(f"{indent}{os.path.basename(root)}/")
-    subindent = ' ' * 4 * (level + 1)
-    for f in files:
-        print(f"{subindent}{f}")
-
-# Set image dimensions and batch size
+# Data loading and preprocessing
 img_height, img_width = 180, 180
 batch_size = 32
-
-# Create training and validation datasets
 train_ds = tf.keras.preprocessing.image_dataset_from_directory(
     data_dir,
     validation_split=0.2,
@@ -62,7 +39,6 @@ train_ds = tf.keras.preprocessing.image_dataset_from_directory(
     image_size=(img_height, img_width),
     batch_size=batch_size
 )
-
 val_ds = tf.keras.preprocessing.image_dataset_from_directory(
     data_dir,
     validation_split=0.2,
@@ -71,92 +47,55 @@ val_ds = tf.keras.preprocessing.image_dataset_from_directory(
     image_size=(img_height, img_width),
     batch_size=batch_size
 )
-
 class_names = train_ds.class_names
-print(class_names)
-
-# Display some sample images
-plt.figure(figsize=(10, 10))
-for images, labels in train_ds.take(1):
-    for i in range(9):
-        ax = plt.subplot(3, 3, i + 1)
-        plt.imshow(images[i].numpy().astype("uint8"))
-        plt.title(class_names[labels[i]])
-        plt.axis("off")
 
-# Enhanced data augmentation
+# Data augmentation
 data_augmentation = keras.Sequential(
     [
         layers.RandomFlip("horizontal", input_shape=(img_height, img_width, 3)),
-        layers.RandomRotation(0.2),
-        layers.RandomZoom(0.2),
-        layers.RandomContrast(0.2),
+        layers.RandomRotation(0.1),
+        layers.RandomZoom(0.1),
         layers.RandomBrightness(0.2),
+        layers.RandomContrast(0.2),
     ]
 )
 
-# Display augmented images
-plt.figure(figsize=(10, 10))
-for images, _ in train_ds.take(1):
-    for i in range(9):
-        augmented_images = data_augmentation(images)
-        ax = plt.subplot(3, 3, i + 1)
-        plt.imshow(augmented_images[0].numpy().astype("uint8"))
-        plt.axis("off")
-
-# Define a deeper CNN model with more regularization techniques
+# Model definition
 num_classes = len(class_names)
-model = Sequential()
-
-model.add(data_augmentation)
-model.add(layers.Rescaling(1./255))
-
-model.add(layers.Conv2D(32, 3, padding='same', activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
-model.add(layers.BatchNormalization())
-model.add(layers.MaxPooling2D())
-
-model.add(layers.Conv2D(64, 3, padding='same', activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
-model.add(layers.BatchNormalization())
-model.add(layers.MaxPooling2D())
-
-model.add(layers.Conv2D(128, 3, padding='same', activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
-model.add(layers.BatchNormalization())
-model.add(layers.MaxPooling2D())
-
-model.add(layers.Conv2D(256, 3, padding='same', activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
-model.add(layers.BatchNormalization())
-model.add(layers.MaxPooling2D())
-
-model.add(layers.Conv2D(512, 3, padding='same', activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
-model.add(layers.BatchNormalization())
-model.add(layers.MaxPooling2D())
-
-model.add(layers.Dropout(0.5))
-model.add(layers.Flatten())
-
-model.add(layers.Dense(256, activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
-model.add(layers.Dropout(0.5))
-
-model.add(layers.Dense(num_classes, activation='softmax', name="outputs"))
-
-model.compile(optimizer=keras.optimizers.Adam(learning_rate=1e-4),
+model = Sequential([
+    data_augmentation,
+    layers.Rescaling(1./255),
+    layers.Conv2D(16, 3, padding='same', activation='relu'),
+    layers.MaxPooling2D(),
+    layers.Conv2D(32, 3, padding='same', activation='relu'),
+    layers.MaxPooling2D(),
+    layers.Conv2D(64, 3, padding='same', activation='relu'),
+    layers.MaxPooling2D(),
+    layers.Conv2D(128, 3, padding='same', activation='relu'),
+    layers.MaxPooling2D(),
+    layers.Dropout(0.5),
+    layers.Flatten(),
+    layers.Dense(256, activation='relu'),
+    layers.Dense(num_classes, activation='softmax', name="outputs")
+])
+
+optimizer = keras.optimizers.Adam(learning_rate=0.001)
+lr_scheduler = keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3)
+early_stopping = keras.callbacks.EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)
+
+model.compile(optimizer=optimizer,
               loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
               metrics=['accuracy'])
 
 model.summary()
 
-# Implement early stopping
-from tensorflow.keras.callbacks import EarlyStopping
-
-early_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)
-
 # Train the model
-epochs = 30
+epochs = 15
 history = model.fit(
     train_ds,
     validation_data=val_ds,
     epochs=epochs,
-    callbacks=[early_stopping]
+    callbacks=[lr_scheduler, early_stopping]
 )
 
 # Define category descriptions
@@ -175,37 +114,32 @@ category_descriptions = {
     "Weevils": "Weevils are a type of beetle with a long snout, known for being pests to crops and stored grains."
 }
 
-# Define the prediction function
+# Prediction function
 def predict_image(img):
     img = np.array(img)
     img_resized = tf.image.resize(img, (180, 180))
     img_4d = tf.expand_dims(img_resized, axis=0)
     prediction = model.predict(img_4d)[0]
-    predicted_class = np.argmax(prediction)
-    predicted_label = class_names[predicted_class]
-    predicted_description = category_descriptions[predicted_label]
-    return {predicted_label: f"{float(prediction[predicted_class]):.2f} - {predicted_description}"}
-
-# Set up Gradio interface
+    top_3_indices = prediction.argsort()[-3:][::-1]
+    results = {}
+    for i in top_3_indices:
+        class_name = class_names[i]
+        results[class_name] = f"{float(prediction[i]):.2f} - {category_descriptions[class_name]}"
+    return results
+
+# Gradio interface setup
 image = gr.Image()
-label = gr.Label(num_top_classes=1)
-
-# Define custom CSS for background image
+label = gr.Label(num_top_classes=3)
 custom_css = """
-body {
-    background-image: url('extracted_files/Pest_Dataset/bees/bees (444).jpg');
-    background-size: cover;
-    background-repeat: no-repeat;
-    background-attachment: fixed;
-    color: white;
-}
+body {background-color: #f5f5f5;}
+.gradio-container {border: 1px solid #ccc; border-radius: 10px; padding: 20px;}
 """
 
 gr.Interface(
     fn=predict_image,
     inputs=image,
     outputs=label,
-    title="Welcome to Agricultural Pest Image Classification",
-    description="The image data set used was obtained from Kaggle and has a collection of 12 different types of agricultural pests: Ants, Bees, Beetles, Caterpillars, Earthworms, Earwigs, Grasshoppers, Moths, Slugs, Snails, Wasps, and Weevils",
+    title="Agricultural Pest Image Classification",
+    description="Identify 12 types of agricultural pests from images. This model was trained on a dataset from Kaggle.",
     css=custom_css
 ).launch(debug=True)