app.py

import gradio as gr
from ultralytics import YOLO
import cv2
import numpy as np
import os
import requests
import torch
import huggingface_hub

# Initialize ZeroGPU 
zero_gpu_is_available = huggingface_hub.utils.is_google_colab() or huggingface_hub.utils.is_notebook()
if zero_gpu_is_available:
    from accelerate import Accelerator
    accelerator = Accelerator()


# Load the model file
model_path = "yolov8x-doclaynet-epoch64-imgsz640-initiallr1e-4-finallr1e-5.pt"
if not os.path.exists(model_path):
    # Download the model file if it doesn't exist
    model_url = "https://huggingface.co/DILHTWD/documentlayoutsegmentation_YOLOv8_ondoclaynet/resolve/main/yolov8x-doclaynet-epoch64-imgsz640-initiallr1e-4-finallr1e-5.pt"
    response = requests.get(model_url)
    with open(model_path, "wb") as f:
        f.write(response.content)

# Load the document segmentation model
docseg_model = YOLO(model_path) 

if zero_gpu_is_available:
    docseg_model.to(accelerator.device)  # Put the model on the accelerator's device.


def process_image(image):
    try:
        # Convert image to the format YOLO model expects
        image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)

        # If Zero GPU, move image to accelerator
        if zero_gpu_is_available:
            image = torch.from_numpy(image).to(accelerator.device)

        results = docseg_model.predict(image)
        result = results[0]  # Get the first (and usually only) result
        
        # Extract annotated image from results
        annotated_img = result.plot() 
        annotated_img = cv2.cvtColor(annotated_img, cv2.COLOR_BGR2RGB)

        # Prepare detected areas and labels as text output
        detected_areas_labels = "\n".join(
            [f"{box.label.upper()}: {box.conf:.2f}" for box in result.boxes]
        )
    except Exception as e:
        return None, f"Error during processing: {e}"  # Error handling

    return annotated_img, detected_areas_labels

# The rest of the code remains the same (Gradio interface)