app.py

import streamlit as st
from PIL import Image
import numpy as np
import tensorflow as tf
from tensorflow.keras.preprocessing import image

# Function to preprocess the uploaded image
def preprocess_uploaded_image(uploaded_image, target_size):
    img = Image.open(uploaded_image)
    img = img.resize(target_size)
    img_array = image.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0)
    return img_array

# Function to load the model and make predictions
def predict_image_class(model_path, uploaded_image, target_size):
    try:
        loaded_model = tf.keras.models.load_model(model_path)
        img = preprocess_uploaded_image(uploaded_image, target_size)
        prediction = loaded_model.predict(img)
        class_idx = np.argmax(prediction)
        return class_idx
    except Exception as e:
        st.error(f"Error loading the model: {e}")
        return None

def main():
    st.title("Heart Disease Image Classifier")
    uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])

    if uploaded_image is not None:
        st.image(uploaded_image, caption="Uploaded Image", use_column_width=True)
        st.write("")
        with st.spinner("Classifying..."):
            # Classify the uploaded image
            class_idx = predict_image_class("model.h5", uploaded_image, target_size=(224, 224))

        if class_idx is not None:
            if class_idx == 0:
                st.write("The patient doesn't have heart disease")
            else:
                st.write("The patient has heart disease")
        else:
            st.error("Failed to classify the image. Please try again.")

# Run the Streamlit app
if __name__ == "__main__":
    main()