Code Editor for app.py

import streamlit as st
from PIL import Image
import numpy as np
import tensorflow as tf
import io

# Set page title and description
st.title("Face Mask Detection")
st.write("Upload an image to check if the person is wearing a mask or not.")

# Load the pre-trained model
@st.cache_resource
def load_model():
    try:
        model = tf.keras.models.load_model('mask_detection_model.h5')
        return model
    except:
        st.error("Error: Model file not found. Please ensure 'mask_detection_model.h5' is in the same directory.")
        return None

model = load_model()

def preprocess_image(image):
    # Resize image to match model's expected sizing
    image = image.resize((224, 224))
    # Convert image to array
    image_array = np.array(image)
    # Normalize pixel values
    image_array = image_array / 255.0
    # Add batch dimension
    image_array = np.expand_dims(image_array, axis=0)
    return image_array

# Create file uploader
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    # Display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Image', use_column_width=True)
    
    # Add a button to perform detection
    if st.button("Detect Mask"):
        if model is not None:
            # Preprocess the image
            processed_image = preprocess_image(image)
            
            # Make prediction
            try:
                prediction = model.predict(processed_image)
                probability = prediction[0][0]
                
                # Display result
                st.write("### Detection Result")
                if probability > 0.5:
                    st.success(f"Mask detected! (Confidence: {probability:.2%})")
                    st.balloons()
                else:
                    st.error(f"No mask detected! (Confidence: {(1-probability):.2%})")
                
                # Display probability bar
                st.progress(float(probability))
                
            except Exception as e:
                st.error(f"Error during prediction: {str(e)}")
        else:
            st.error("Model not loaded properly. Please check if the model file exists.")

# Add information about the model
st.sidebar.title("About")
st.sidebar.info("""
This app uses a deep learning model trained to detect whether a person is wearing a face mask or not.
                
To use:
1. Upload an image
2. Click 'Detect Mask'
3. View the results
""")