app.py

import os  
from PIL import Image
import requests
import gradio as gr
import tensorflow as tf
import numpy as np

# Download the model at runtime
MODEL_URL = "https://huggingface.co/Venisri2006/psoriasis-severity-classifier/resolve/main/psoriasis_classifier.keras"
MODEL_PATH = "updated_model.keras"

# Download the model if it does not exist
if not os.path.exists(MODEL_PATH):
    print("Downloading model...")
    r = requests.get(MODEL_URL, allow_redirects=True)
    open(MODEL_PATH, "wb").write(r.content)

# Load model
model = tf.keras.models.load_model(MODEL_PATH)

# Define classes
classes = ["Mild", "Moderate", "Severe"]

def predict_psoriasis(image):
    image = image.resize((224, 224))  # Resize to model input size
    image = np.array(image) / 255.0   # Normalize
    image = np.expand_dims(image, axis=0)  # Add batch dimension

    prediction = model.predict(image)[0]
    severity = classes[np.argmax(prediction)]
    return {"Severity": severity, "Confidence": float(np.max(prediction))}

# Create Gradio interface
iface = gr.Interface(
    fn=predict_psoriasis,
    inputs=gr.Image(type="pil"),
    outputs=gr.Label(),
    title="Psoriasis Severity Classifier",
    description="Upload an image of skin affected by psoriasis to predict severity (Mild, Moderate, Severe)."
)

iface.launch()