app.py

import gradio as gr
import numpy as np
import tensorflow as tf
import cv2

# Load the trained model
model = tf.keras.models.load_model("Handwritten_model.h5")  # Make sure the filename matches your uploaded model

def predict_digit(image):
    # Preprocess the image
    img = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)  # Convert to grayscale
    img = cv2.resize(img, (28, 28))  # Resize to 28x28 pixels
    img = np.invert(img)  # Invert the image colors
    img = img.astype("float32") / 255  # Normalize to [0, 1]
    img = img.reshape(1, 28, 28)  # Reshape for the model input

    # Make prediction
    prediction = model.predict(img)
    predicted_class = np.argmax(prediction)
    return predicted_class

# Define the Gradio interface using the updated API
gr.Interface(
    fn=predict_digit,
    inputs=gr.Image(type="numpy", label="Upload a digit image"),  # Updated to use gr.Image
    outputs="text",
    title="Handwritten Digit Recognition",
    description="Upload an image of a handwritten digit, and the model will predict which digit it is."
).launch()