app.py

import gradio as gr
import tensorflow as tf
from tensorflow.keras.applications import ResNet152, preprocess_input, decode_predictions
from tensorflow.keras.preprocessing.image import img_to_array
from PIL import Image
import numpy as np

# Load the pre-trained ResNet152 model
MODEL_PATH = "resnet152-image-classifier"  # Directory where the model is saved
model = tf.keras.models.load_model(MODEL_PATH)

def predict_image(image):
    """
    This function processes the uploaded image and returns the top 3 predictions.
    """
    # Preprocess the image
    image = image.resize((224, 224))  # ResNet152 expects 224x224 input
    image_array = img_to_array(image)
    image_array = preprocess_input(image_array)  # Normalize the image
    image_array = np.expand_dims(image_array, axis=0)  # Add batch dimension

    # Get predictions
    predictions = model.predict(image_array)
    decoded_predictions = decode_predictions(predictions, top=3)[0]

    # Format predictions as a dictionary
    results = {label: f"{confidence * 100:.2f}%" for _, label, confidence in decoded_predictions}
    return results

# Create the Gradio interface
interface = gr.Interface(
    fn=predict_image,
    inputs=gr.Image(type="pil"),  # Accepts an image input
    outputs=gr.Label(num_top_classes=3),  # Shows top 3 predictions with confidence
    title="ResNet152 Image Classifier",
    description="Upload an image, and the model will predict what's in the image.",
    examples=["dog.jpg", "cat.jpg"],  # Example images for users to test
)

# Launch the Gradio app
if __name__ == "__main__":
    interface.launch()