import gradio as gr import tensorflow as tf import numpy as np from PIL import Image # Load the trained model model = tf.keras.models.load_model('Skin Cancer.h5') # Preprocess function to prepare image for model def preprocess_image(img): img = img.resize((224, 224)) # Resize as per model input img = np.array(img) / 255.0 # Normalize img = np.expand_dims(img, axis=0) return img # Prediction function def predict(image): img = preprocess_image(image) prediction = model.predict(img)[0][0] if prediction > 0.5: result = "Cancer Detected ❌" confidence = f"Confidence: {prediction*100:.2f}%" else: result = "No Cancer ✅" confidence = f"Confidence: {(1 - prediction)*100:.2f}%" return result, confidence # Gradio UI iface = gr.Interface( fn=predict, inputs=gr.Image(type="pil", label="Upload Skin Image"), outputs=[gr.Text(label="Prediction"), gr.Text(label="Confidence")], title="Skin Cancer Detection App", description="Upload a skin image to detect whether it has cancer or not using CNN model." ) # Launch app iface.launch()