app.py

import tensorflow as tf
import gradio as gr
import numpy as np
from PIL import Image
from tensorflow.keras.preprocessing import image

# ---------------------------------------------------------
# Load trained model (inference only)
# ---------------------------------------------------------
MODEL_PATH = "breast_cancer_model.h5"

model = tf.keras.models.load_model(
    "breast_cancer_model.keras",
    compile=False
)

# ---------------------------------------------------------
# Prediction function
# ---------------------------------------------------------
def predict_image(img: Image.Image):
    """
    Takes a PIL image as input and returns prediction text
    """
    # Resize image to model input size
    img = img.resize((224, 224))

    # Convert to array and normalize
    img_array = image.img_to_array(img) / 255.0
    img_array = np.expand_dims(img_array, axis=0)

    # Predict
    prediction = model.predict(img_array)[0][0]

    # Output
    if prediction > 0.5:
        return f"Cancer Detected (Confidence: {prediction:.2f})"
    else:
        return f"Healthy (Confidence: {1 - prediction:.2f})"


# ---------------------------------------------------------
# Gradio Interface
# ---------------------------------------------------------
interface = gr.Interface(
    fn=predict_image,
    inputs=gr.Image(type="pil", label="Upload Histopathology Image"),
    outputs=gr.Textbox(label="Prediction Result"),
    title="Breast Cancer Detection System",
    description=(
        "Upload a breast histopathology image to detect cancer using a "
        "VGG16-based deep learning model.\n\n"
        "⚠️ This tool is for research and educational purposes only."
    ),
    allow_flagging="never"
)

# ---------------------------------------------------------
# Launch App
# ---------------------------------------------------------
if __name__ == "__main__":
    interface.launch()