Update app.py

app.py

@@ -1,175 +1,125 @@
-import gradio as gr
+batch_size = 32
+img_height = 180
+img_width = 180
+
+train_ds = tf.keras.utils.image_dataset_from_directory(
+  data_dir,
+  validation_split=0.2,
+  subset="training",
+  seed=123,
+  image_size=(img_height, img_width),
+  batch_size=batch_size)
+
+val_ds = tf.keras.utils.image_dataset_from_directory(
+  data_dir,
+  validation_split=0.2,
+  subset="validation",
+  seed=123,
+  image_size=(img_height, img_width),
+  batch_size=batch_size)
+
+class_names = train_ds.class_names
+print(class_names)
+
 import matplotlib.pyplot as plt
-import numpy as np
-import os
-import PIL
-import tensorflow as tf
 
-from tensorflow import keras
-from tensorflow.keras import layers
-from tensorflow.keras.models import Sequential
-from PIL import Image
-import gdown
-import zipfile
-import pathlib
-
-# Define the Google Drive shareable link
-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)
-
-# Convert the extracted directory path to a pathlib.Path object
-data_dir = pathlib.Path(extracted_path)
-
-# Print the directory structure to debug
-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}")
-
-# Path to the dataset directory
-data_dir = pathlib.Path('extracted_files/Pest_Dataset')
-
-img_height, img_width = 180, 180
-batch_size = 32
+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")
 
-# Load training and validation datasets
-train_ds = tf.keras.preprocessing.image_dataset_from_directory(
-    data_dir,
-    validation_split=0.2,
-    subset="training",
-    seed=123,
-    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,
-    subset="validation",
-    seed=123,
-    image_size=(img_height, img_width),
-    batch_size=batch_size
-)
+for image_batch, labels_batch in train_ds:
+  print(image_batch.shape)
+  print(labels_batch.shape)
+  break
+
+
+AUTOTUNE = tf.data.AUTOTUNE
+
+train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
+val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
+
+normalization_layer = layers.Rescaling(1./255)
+
+normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
+image_batch, labels_batch = next(iter(normalized_ds))
+first_image = image_batch[0]
+# Notice the pixel values are now in `[0,1]`.
+print(np.min(first_image), np.max(first_image))
 
-# Define data augmentation layers
 data_augmentation = keras.Sequential(
-    [
-        layers.RandomFlip("horizontal", input_shape=(img_height, img_width, 3)),
-        layers.RandomRotation(0.1),
-        layers.RandomZoom(0.1),
-    ]
+  [
+    layers.RandomFlip("horizontal",
+                      input_shape=(img_height,
+                                  img_width,
+                                  3)),
+    layers.RandomRotation(0.1),
+    layers.RandomZoom(0.1),
+  ]
 )
 
-# Define the model
-num_classes = len(train_ds.class_names)
+
+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")
+
+num_classes = len(class_names)
+
 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.Dropout(0.2),
-    layers.Flatten(),
-    layers.Dense(128, activation='relu'),
-    layers.Dense(num_classes, activation='softmax', name="outputs")  # Use softmax here
+  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.Dropout(0.2),
+  layers.Flatten(),
+  layers.Dense(128, activation='relu'),
+  layers.Dense(num_classes, name="outputs")
 ])
 
 model.compile(optimizer='adam',
-              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),  # Change from_logits to False
+              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
               metrics=['accuracy'])
 
 model.summary()
 
-# Train the model
 epochs = 15
 history = model.fit(
-    train_ds,
-    validation_data=val_ds,
-    epochs=epochs
+  train_ds,
+  validation_data=val_ds,
+  epochs=epochs
 )
 
-# Plot training history
-plt.plot(history.history['accuracy'], label='accuracy')
-plt.plot(history.history['val_accuracy'], label='val_accuracy')
-plt.xlabel('Epoch')
-plt.ylabel('Accuracy')
-plt.legend()
-plt.show()
-
-plt.plot(history.history['loss'], label='loss')
-plt.plot(history.history['val_loss'], label='val_loss')
-plt.xlabel('Epoch')
-plt.ylabel('Loss')
-plt.legend()
-plt.show()
-
-
-
-
-# Define category descriptions
-category_descriptions = {
-    "Ants": "Ants are small insects known for their complex social structures and teamwork.",
-    "Bees": "Bees are flying insects known for their role in pollination and producing honey.",
-    "Beetles": "Beetles are a group of insects with hard exoskeletons and wings. They are the largest order of insects.",
-    "Caterpillars": "Caterpillars are the larval stage of butterflies and moths, known for their voracious appetite.",
-    "Earthworms": "Earthworms are segmented worms that are crucial for soil health and nutrient cycling.",
-    "Earwigs": "Earwigs are insects with pincers on their abdomen and are known for their nocturnal activity.",
-    "Grasshoppers": "Grasshoppers are insects known for their powerful hind legs, which they use for jumping.",
-    "Moths": "Moths are nocturnal insects related to butterflies, known for their attraction to light.",
-    "Slugs": "Slugs are soft-bodied mollusks that are similar to snails but lack a shell.",
-    "Snails": "Snails are mollusks with a coiled shell, known for their slow movement and slimy trail.",
-    "Wasps": "Wasps are stinging insects that can be solitary or social, and some species are important pollinators.",
-    "Weevils": "Weevils are a type of beetle with a long snout, known for being pests to crops and stored grains."
-}
+import gradio as gr
+import numpy as np
+import tensorflow as tf
 
-# Define the 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}"}
+    return {class_names[i]: float(prediction[i]) for i in range(len(class_names))}
+
 
-# Set up Gradio interface
 image = gr.Image()
-label = gr.Label(num_top_classes=1)
+label = gr.Label(num_top_classes=12)
 
 # Define custom CSS for background image
 custom_css = """
 body {
-    background-image: url('extracted_files/Pest_Dataset/bees/bees (444).jpg');
+    background-image: url('\extracted_files\Pest_Dataset\bees\bees (444).jpg');
     background-size: cover;
     background-repeat: no-repeat;
     background-attachment: fixed;
@@ -181,8 +131,7 @@ 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="Pest Classification",
+    description="Upload an image of a pest to classify it into one of the predefined categories.",
     css=custom_css
-).launch(debug=True)
-
+).launch(debug=True)