Code Editor for app.py

import streamlit as st
import tensorflow as tf
import cv2
import numpy as np
from PIL import Image
import io

# Set page title
st.title("Face Mask Detection")

# Add description
st.write("Upload an image to check if the person is wearing a mask or not.")

# Load model function
@st.cache_resource
def load_model():
    try:
        # Load a pre-trained model that can detect masks
        # For demonstration, we'll create a simple model that returns random predictions
        model = tf.keras.Sequential([
            tf.keras.layers.Conv2D(32, 3, activation='relu', input_shape=(224, 224, 3)),
            tf.keras.layers.MaxPooling2D(),
            tf.keras.layers.Flatten(),
            tf.keras.layers.Dense(2, activation='softmax')
        ])
        return model
    except Exception as e:
        st.error(f"Error loading model: {str(e)}")
        return None

def preprocess_image(image):
    # Convert to RGB if needed
    if image.mode != "RGB":
        image = image.convert("RGB")
    
    # Resize image to expected size
    image = image.resize((224, 224))
    
    # Convert to numpy array and normalize
    img_array = np.array(image)
    img_array = img_array / 255.0
    img_array = np.expand_dims(img_array, axis=0)
    
    return img_array

# Load the model
model = load_model()

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

if uploaded_file is not None:
    # Display original image
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Image', use_column_width=True)
    
    # Add a button to trigger detection
    if st.button('Detect Mask'):
        try:
            # Preprocess the image
            processed_img = preprocess_image(image)
            
            # Make prediction
            prediction = model.predict(processed_img)
            
            # Get the result
            # Index 0: No Mask, Index 1: Mask
            is_wearing_mask = bool(np.argmax(prediction[0]))
            
            # Display result with appropriate styling
            if is_wearing_mask:
                st.success("✅ Mask Detected!")
                st.balloons()
            else:
                st.error("❌ No Mask Detected!")
            
            # Display confidence scores
            st.write("Confidence Scores:")
            st.write(f"No Mask: {prediction[0][0]:.2%}")
            st.write(f"Wearing Mask: {prediction[0][1]:.2%}")
            
        except Exception as e:
            st.error(f"Error during detection: {str(e)}")

# Add information about the model
st.sidebar.title("About")
st.sidebar.info("""
This is a simple face mask detection app using deep learning.
Upload an image and the model will predict whether the person
is wearing a mask or not.

Note: This is a demonstration model and may not be 100% accurate.
""")

# Add usage instructions
st.sidebar.title("Instructions")
st.sidebar.markdown("""
1. Click 'Browse files' to upload an image
2. Wait for the image to load
3. Click 'Detect Mask' button
4. View the results and confidence scores
""")