import gradio as gr
import json

from ultralyticsplus import YOLO, render_result

# Model Heading and Description
model_heading = "YOLOv8 NDL-DocL Datasets"
description = """YOLOv8 NDL-DocL Datasets Gradio demo for object detection. Upload an image or click an example image to use."""

article = "<p style='text-align: center'>YOLOv5 NDL-DocL Datasets is an object detection model trained on the <a href=\"https://github.com/ndl-lab/layout-dataset\">NDL-DocL Datasets</a>.</p>"

image_path= [
       
    ['『源氏物語』(東京大学総合図書館所蔵).jpg', 0.25, 0.45],
     ['『源氏物語』(京都大学所蔵).jpg', 0.25, 0.45],
      ['『平家物語』(国文学研究資料館提供).jpg', 0.25, 0.45]
]

# Load YOLO model
model = YOLO('nakamura196/yolov8-ndl-layout')

def yolov8_img_inference(
    image: gr.Image = None,
    conf_threshold: gr.Slider = 0.25,
    iou_threshold: gr.Slider = 0.45,
):
    """
    YOLOv8 inference function
    Args:
        image: Input image
        conf_threshold: Confidence threshold
        iou_threshold: IOU threshold
    Returns:
        Rendered image
    """
    results = model.predict(image, conf=conf_threshold, iou=iou_threshold, device="cpu")
    render = render_result(model=model, image=image, result=results[0])            

    json_data = json.loads(results[0].tojson())
    
    return render, json_data

    
inputs_image = [
    gr.Image(type="filepath", label="Input Image"),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold"),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold"),
]

outputs_image =[
    gr.Image(type="filepath", label="Output Image"),
    gr.JSON(label="Output JSON")
]
demo = gr.Interface(
    fn=yolov8_img_inference,
    inputs=inputs_image,
    outputs=outputs_image,
    title=model_heading,
    description=description,
    examples=image_path,
    article=article,
    cache_examples=False
)

demo.launch(share=False)