app.py

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

# Load the pre-trained model
model_path = 'cnn_tumor.h5'
model = tf.keras.models.load_model(model_path)

def make_prediction(img, model):
    img = img.resize((128, 128))
    img = np.array(img) / 255.0  # Normalize the image
    input_img = np.expand_dims(img, axis=0)
    res = model.predict(input_img)
    return res

# Function to load the CSS file and apply it
def local_css(file_name):
    with open(file_name) as f:
        st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)

# Set page config
st.set_page_config(page_title='Tumor Detection App', layout='centered')

# Load the custom CSS file
local_css("style.css")

# Add a title with emojis inside the glass div
st.markdown("""
    <div class="glass">
        <h1>Tumor Detection App 🧠🔍</h1>
        <p>Upload a brain scan image to detect the presence of a tumor.</p>
    </div>
""", unsafe_allow_html=True)

st.sidebar.header('Upload Your Image')
uploaded_file = st.sidebar.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    # Load the image
    image = Image.open(uploaded_file)
    
    # Center the uploaded image using Streamlit's columns
    col1, col2, col3 = st.columns([1, 2, 1])
    with col2:
        st.image(image, caption='Uploaded Image', use_column_width=True)

    # Make a prediction
    with st.spinner('Making prediction...'):
        result = make_prediction(image, model)
        
        # Display the result with a glass effect
        result_message = "Tumor Detected" if result > 0.5 else "No Tumor Detected"
        st.markdown(f"""
            <div class="glass">
                <h2>{result_message}</h2>
            </div>
        """, unsafe_allow_html=True)
else:
    st.markdown("<p></p>", unsafe_allow_html=True)