app.py

import gradio as gr
from ultralytics import YOLO
import os

# Load pre-trained YOLOv8 models
docseg_model1 = YOLO("yolov8x-doclaynet-epoch64-imgsz640-initiallr1e-4-finallr1e-5.pt")
docseg_model2 = YOLO("path/to/your/second/model.pt")  # Replace with your second model's path

# Available models
MODELS = {
    "DocLayNet YOLOv8": docseg_model1,
    # "Your Second Model": docseg_model2  # Uncomment and add more as needed
}

def process_image(image, model_name):
    try:
        # Select the model
        model = MODELS[model_name]

        # Process the image
        results = model(source=image, save=False, show_labels=True, show_conf=True, show_boxes=True)
        result = results[0]
        
        # Extract the annotated image and the labels/confidence scores
        annotated_image = result.plot()
        detected_areas_labels = "\n".join(
            [f"{box.label.upper()}: {box.conf:.2f}" for box in result.boxes]
        )

        return annotated_image, detected_areas_labels
    except Exception as e:
        return None, f"Error processing image: {e}"
    


# Create the Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("# Document Segmentation Demo")
    
    # Input Components
    with gr.Row():
        input_image = gr.Image(type="pil", label="Upload Image")
        model_dropdown = gr.Dropdown(list(MODELS.keys()), label="Select Model", value=list(MODELS.keys())[0])

    # Output Components
    output_image = gr.Image(type="pil", label="Annotated Image")
    output_text = gr.Textbox(label="Detected Areas and Labels")

    # Button to trigger inference
    btn = gr.Button("Run Document Segmentation")
    btn.click(fn=process_image, inputs=[input_image, model_dropdown], outputs=[output_image, output_text])

# Launch the demo
demo.launch()