app.py

import gradio as gr
import numpy as np
from PIL import Image
from keras.models import load_model

# Load your pre-trained model (make sure the model file is in the same directory)
model = load_model('brain_tumor_model.h5')

# Function to process image and make predictions
def predict_image(image):
    # Resize the image
    img = image.resize((128, 128))

    # Convert the image to a NumPy array
    img = np.array(img)

    # Check if the image has 3 color channels
    if img.shape == (128, 128):  # If grayscale, convert to RGB
        img = np.stack((img,) * 3, axis=-1)

    # Add a batch dimension
    img = np.expand_dims(img, axis=0)

    # Make the prediction
    prediction = model.predict(img)

    # Get the predicted class and confidence level
    predicted_class = np.argmax(prediction)
    confidence = np.max(prediction)

    # Return the results
    if predicted_class == 0:
        return f'No tumor detected. Confidence: {confidence:.2f}'
    else:
        return f'Tumor detected. Confidence: {confidence:.2f}'

# Create custom CSS for background color
css = """
body {
    background-color: #f0f4f7;
}
"""


# Create the Gradio interface
iface = gr.Interface(
    fn=predict_image,
    inputs=gr.Image(type="pil"),
    outputs=gr.Textbox(),
    title="Brain Tumor Detection AI App",
    description="Upload a Magnetic Resonance Imaging (MRI) scan image to detect brain tumors.",
    css=css,  # Apply the custom background color
    #theme="dark",  # Apply a dark theme to the interface
    flagging_options=["Incorrect Diagnosis", "Image Not Clear", "Model Error"],  # Add flagging options
)

# Launch the interface
iface.launch()