Hugging Face's logo

Spaces:
gradio
/
YOLOv10-webcam-stream
Sleeping

App Files Community
YOLOv10-webcam-stream
File size: 3,093 Bytes 
8b2cbe6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2172fc2
8b2cbe6
2172fc2
8b2cbe6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f23b96a
 
8b2cbe6
 
 
 
 
f23b96a
8b2cbe6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c5b9185
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
 
import PIL.Image as Image
import gradio as gr

from ultralytics import ASSETS, 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()