app.py

import gradio as gr
from ultralytics import YOLO
import cv2
import numpy as np
#import spaces

# Load the trained model
model_path = 'best.pt'  # Replace with the path to your trained .pt file
model = YOLO(model_path)

# Function to perform inference on an image
#@spaces.GPU
def infer_image(image):
    # Convert the image from BGR to RGB
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    
    # Perform inference
    results = model(image_rgb)
    
    # Extract results and annotate image
    for result in results:
        for box in result.boxes:
            x1, y1, x2, y2 = box.xyxy[0]
            cls = int(box.cls[0])
            conf = float(box.conf[0])
            
            # Draw bounding box
            cv2.rectangle(image, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
            # Draw label
            label = f'{model.names[cls]} {conf:.2f}'
            cv2.putText(image, label, (int(x1), int(y1) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
    
    return image

# Create Gradio interface
iface = gr.Interface(
    fn=infer_image, 
    inputs=gr.Image(type="numpy", label="Upload an Image"),
    outputs=gr.Image(type="numpy", label="Annotated Image"),
    title="Fast document layout analysis based on YOLOv8",
    description="Upload an image to get document layout analysis results."
)

# Launch the app
iface.launch()