app.py

import gradio as gr
from ultralytics import YOLO
import spaces

@spaces.GPU(duration=200)
def LeYOLO_inference(image, model_id, image_size, conf_threshold, iou_threshold):
    model = YOLO(f"{model_id}.pt")
    results = model(source=image, imgsz=image_size, iou=iou_threshold, conf=conf_threshold, verbose=False)[0]
    

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=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.25,
                )
                iou_threshold = gr.Slider(
                    label="IoU Threshold",
                    minimum=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.45,
                )
                yolov10_infer = gr.Button(value="Detect Objects")

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

        yolov10_infer.click(
            fn=yolov10_inference,
            inputs=[
                image,
                model_id,
                image_size,
                conf_threshold,
                iou_threshold,
            ],
            outputs=[output_image],
        )

        gr.Examples(
            examples=[
                [
                    "dog.jpeg",
                    "yolov10x",
                    640,
                    0.25,
                    0.45,
                ],
                [
                    "huggingface.jpg",
                    "yolov10m",
                    640,
                    0.25,
                    0.45,
                ],
                [
                    "zidane.jpg",
                    "yolov10b",
                    640,
                    0.25,
                    0.45,
                ],
            ],
            fn=LeYOLO_inference,
            inputs=[
                image,
                model_id,
                image_size,
                conf_threshold,
                iou_threshold,
            ],
            outputs=[output_image],
            cache_examples="lazy",
        )

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'>
        Follow me for more!
        <a href='https://twitter.com/kadirnar_ai' target='_blank'>Twitter</a> | <a href='https://github.com/kadirnar' target='_blank'>Github</a> | <a href='https://www.linkedin.com/in/kadir-nar/' target='_blank'>Linkedin</a>  | <a href='https://www.huggingface.co/kadirnar/' target='_blank'>HuggingFace</a>
        </h3>
        """)
    with gr.Row():
        with gr.Column():
            app()

gradio_app.launch(debug=True)