app.py

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

path_to_model = "nova.h5"

# Load the trained model
model = tf.keras.models.load_model(path_to_model)

# Set the default height and width of the uploaded image
IMG_HEIGHT = 180
IMG_WIDTH = 180

# Define a function to preprocess the image
def preprocess_image(image):
    # Resize the image to the expected input size of the model
    img = image.resize((IMG_HEIGHT, IMG_WIDTH))
    # Convert the image to a numpy array
    img_array = img_to_array(img)
    # Normalize the pixel values
    img_array = img_array / 255.0
    # Reshape the image array to match the input shape of the model
    img_array = np.reshape(img_array, (1, IMG_HEIGHT, IMG_WIDTH, 3))
    return img_array

# Create the Streamlit app
def main():
    # Set the title and a brief description
    st.title("Nova'23 Classification model")    
    # Add an image upload option
    uploaded_image = st.file_uploader('Upload an image', type=['jpg', 'jpeg', 'png'])
    
    # If an image has been uploaded, display it and make a prediction
    if uploaded_image is not None:
        # Display the uploaded image
        image = Image.open(uploaded_image)
        st.image(image, caption='Uploaded Image', use_column_width=True)
        
        # Preprocess the image for the model
        input_image = preprocess_image(image)
        
        # Make a prediction using the model
        prediction = model.predict(input_image)
        
        # Display the prediction
        if prediction[0][0] > prediction[0][1]:
            st.write('Prediction: Normal')
        else:
            st.write('Prediction: Pneumonia')

if __name__ == '__main__':
    main()