app.py

import gradio as gr
from tensorflow.keras.models import load_model
from tensorflow.keras.applications.densenet import preprocess_input
from PIL import Image
import numpy as np

# Ukuran gambar dan load model
IMG_SIZE = (224, 224)
model = load_model("xray_class.weights.h5")

# Preprocessing
def preprocess_image(image):
    image = image.convert("RGB")
    image = image.resize(IMG_SIZE)
    image = np.array(image)
    image = preprocess_input(image)
    image = np.expand_dims(image, axis=0)
    return image

# Label sesuai model kamu (ganti sesuai penyakit yang kamu latih)
label_names = ["Infiltration", "Effusion", "Atelectasis"]

# Fungsi prediksi
def predict(image):
    img = preprocess_image(image)
    pred = model.predict(img)[0]
    result = {label: float(f"{val:.2f}") for label, val in zip(label_names, pred)}
    return result

# Interface
interface = gr.Interface(fn=predict, inputs=gr.Image(type="pil"), outputs="label")

if __name__ == "__main__":
    interface.launch()