app.py

import gradio as gr
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')
data_dir = pathlib.Path(data_dir)

bees = list(data_dir.glob('bees/*'))
print(bees[0])
PIL.Image.open(str(bees[0]))

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)

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)

num_classes = len(class_names)

data_augmentation = keras.Sequential(
    [
        layers.RandomFlip("horizontal", input_shape=(img_height, img_width, 3)),
        layers.RandomRotation(0.1),
        layers.RandomZoom(0.1),
    ]
)

# Define a deeper convolutional neural network
model = Sequential([
    data_augmentation,
    normalization_layer,
    layers.Conv2D(32, 3, padding='same', activation='relu', input_shape=(img_height, img_width, 3)),
    layers.MaxPooling2D(),
    layers.Conv2D(64, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(128, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(256, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(512, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(512, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Dropout(0.5),
    layers.Flatten(),
    layers.Dense(1024, activation='relu'),
    layers.Dropout(0.5),
    layers.Dense(num_classes, activation='softmax')
])

# Ensure the input shape is correctly passed
model.build((None, img_height, img_width, 3))

model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.001),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['accuracy'])

model.summary()

epochs = 15
history = model.fit(
    train_ds,
    validation_data=val_ds,
    epochs=epochs
)

def predict_image(img):
    img = np.array(img)
    img_resized = tf.image.resize(img, (img_height, img_width))
    img_4d = tf.expand_dims(img_resized, axis=0)
    prediction = model.predict(img_4d)[0]
    return {class_names[i]: float(prediction[i]) for i in range(len(class_names))}

image = gr.Image()
label = gr.Label(num_top_classes=1)

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;
}
"""

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",
    css=custom_css
).launch(debug=True)