import PIL.Image as Image
import gradio as gr

from ultralytics import YOLOv10

def predict_image(img, model_id, image_size, conf_threshold):
    model = YOLOv10.from_pretrained(f'jameslahm/{model_id}')
    results = model.predict(
        source=img,
        conf=conf_threshold,
        show_labels=True,
        show_conf=True,
        imgsz=image_size,
    )

    for r in results:
        im_array = r.plot()
        im = Image.fromarray(im_array[..., ::-1])

    return im

def app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                image = gr.Image(type="pil", label="Image")
                
                model_id = gr.Dropdown(
                    label="Model",
                    choices=[
                        "yolov10n",
                        "yolov10s",
                        "yolov10m",
                        "yolov10b",
                        "yolov10l",
                        "yolov10x",
                    ],
                    value="yolov10m",
                )
                image_size = gr.Slider(
                    label="Image Size",
                    minimum=320,
                    maximum=1280,
                    step=32,
                    value=640,
                )
                conf_threshold = gr.Slider(
                    label="Confidence Threshold",
                    minimum=0.0,
                    maximum=1.0,
                    step=0.05,
                    value=0.25,
                )
                yolov10_infer = gr.Button(value="Detect Objects")

            with gr.Column():
                output_image = gr.Image(type="pil", label="Annotated Image")

        yolov10_infer.click(
            fn=predict_image,
            inputs=[
                image,
                model_id,
                image_size,
                conf_threshold,
            ],
            outputs=[output_image],
        )

        gr.Examples(
            examples=[
                [
                    "bus.jpg",
                    "yolov10s",
                    640,
                    0.25,
                ],
                [
                    "zidane.jpg",
                    "yolov10s",
                    640,
                    0.25,
                ],
            ],
            fn=predict_image,
            inputs=[
                image,
                model_id,
                image_size,
                conf_threshold,
            ],
            outputs=[output_image],
            cache_examples=True,
        )

gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv10: Real-Time End-to-End Object Detection
    </h1>
    """)
    gr.HTML(
        """
        <h3 style='text-align: center'>
        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
        </h3>
        """)
    with gr.Row():
        with gr.Column():
            app()
if __name__ == '__main__':
    gradio_app.launch()