mobilenet_tb_model

import gradio as gr import numpy as np import tensorflow as tf from tensorflow.keras.models import load_model from tensorflow.keras.preprocessing import image import requests from io import BytesIO

Download the model from Hugging Face

model_url = "https://huggingface.co/almohab/mobilenet_tb_model/resolve/main/mobilenet_tb_model.h5" model_path = "mobilenet_tb_model.h5"

Download the model if not already present

try: open(model_path) except: print("Downloading model...") response = requests.get(model_url) with open(model_path, "wb") as f: f.write(response.content)

Load the model

model = load_model(model_path) labels = ["Normal", "Tuberculosis"] # Adjust based on your classes

Define prediction function

def predict_tb(img): img = img.resize((224, 224)) # Resize image to match MobileNet input size img = image.img_to_array(img) img = np.expand_dims(img, axis=0) img = img / 255.0 # Normalize

prediction = model.predict(img)
result = labels[int(prediction[0] > 0.5)]  # Assume binary classification
return f"Prediction: {result}"

Create Gradio Interface

interface = gr.Interface( fn=predict_tb, inputs=gr.Image(type="pil"), outputs="text", title="Tuberculosis Detection API", description="Upload a chest X-ray image to check if it is normal or tuberculosis." )

Launch the app

interface.launch()