app1.py

import gradio as gr
import numpy as np
from keras.models import load_model
from PIL import Image

# Load the trained model
model = load_model("mnist_model.h5")

# Prediction function
def predict_digit(image):
    image = image.convert('L').resize((28, 28))
    img_array = np.array(image).astype("float32") / 255.0
    img_array = img_array.reshape(1, 28, 28)
    
    prediction = model.predict(img_array)
    predicted_class = np.argmax(prediction)
    confidence = float(np.max(prediction))
    
    return f"Prediction: {predicted_class} (Confidence: {confidence:.2f})"

# Gradio Interface (no shape argument)
interface = gr.Interface(
    fn=predict_digit,
    inputs=gr.Image(type="pil", label="Upload a Digit Image"),
    outputs=gr.Textbox(label="Prediction"),
    title="Handwritten Digit Recognition",
    description="Upload a handwritten digit image (0–9) to classify it using a model trained on the MNIST dataset."
)

interface.launch()