File size: 5,431 Bytes
69a5bd9
 
 
 
e873cda
69a5bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c61a82
69a5bd9
 
1c61a82
69a5bd9
 
 
 
 
 
 
 
 
 
 
1c61a82
69a5bd9
 
 
 
 
 
1c61a82
69a5bd9
 
 
 
 
 
 
 
1c61a82
 
69a5bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e873cda
69a5bd9
 
 
 
 
e873cda
69a5bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c61a82
69a5bd9
 
 
 
 
1c61a82
69a5bd9
 
 
 
 
 
 
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
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
import gradio as gr
import cv2
import tempfile
from ultralytics import YOLOv10


def yolov10_inference(image, video, model_id, image_size, conf_threshold):
    model = YOLOv10.from_pretrained(f'jameslahm/{model_id}')
    if image:
        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold)
        annotated_image = results[0].plot()
        return annotated_image[:, :, ::-1], None
    else:
        video_path = tempfile.mktemp(suffix=".webm")
        with open(video_path, "wb") as f:
            with open(video, "rb") as g:
                f.write(g.read())

        cap = cv2.VideoCapture(video_path)
        fps = cap.get(cv2.CAP_PROP_FPS)
        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))

        output_video_path = tempfile.mktemp(suffix=".webm")
        out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'vp80'), fps, (frame_width, frame_height))

        while cap.isOpened():
            ret, frame = cap.read()
            if not ret:
                break

            results = model.predict(source=frame, imgsz=image_size, conf=conf_threshold)
            annotated_frame = results[0].plot()
            out.write(annotated_frame)

        cap.release()
        out.release()

        return None, output_video_path


def yolov10_inference_for_examples(image, model_path, image_size, conf_threshold):
    annotated_image, _ = yolov10_inference(image, None, model_path, image_size, conf_threshold)
    return annotated_image


def app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                image = gr.Image(type="pil", label="Image", visible=True)
                video = gr.Video(label="Video", visible=False)
                input_type = gr.Radio(
                    choices=["Image", "Video"],
                    value="Image",
                    label="输入类型",
                )
                model_id = gr.Dropdown(
                    label="模型",
                    choices=[
                        "yolov10n",
                        "yolov10s",
                        "yolov10m",
                        "yolov10b",
                        "yolov10l",
                        "yolov10x",
                    ],
                    value="yolov10m",
                )
                image_size = gr.Slider(
                    label="图片大小",
                    minimum=320,
                    maximum=1280,
                    step=32,
                    value=640,
                )
                conf_threshold = gr.Slider(
                    label="置信度阈值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="numpy", label="注释的图像", visible=True)
                output_video = gr.Video(label="注释的视频", visible=False)

        def update_visibility(input_type):
            image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
            video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
            output_image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
            output_video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)

            return image, video, output_image, output_video

        input_type.change(
            fn=update_visibility,
            inputs=[input_type],
            outputs=[image, video, output_image, output_video],
        )

        def run_inference(image, video, model_id, image_size, conf_threshold, input_type):
            if input_type == "Image":
                return yolov10_inference(image, None, model_id, image_size, conf_threshold)
            else:
                return yolov10_inference(None, video, model_id, image_size, conf_threshold)


        yolov10_infer.click(
            fn=run_inference,
            inputs=[image, video, model_id, image_size, conf_threshold, input_type],
            outputs=[output_image, output_video],
        )

        gr.Examples(
            examples=[
                [
                    "./bus.jpg",
                    "yolov10s",
                    640,
                    0.25,
                ],
                [
                    "./zidane.jpg",
                    "yolov10s",
                    640,
                    0.25,
                ],
            ],
            fn=yolov10_inference_for_examples,
            inputs=[
                image,
                model_id,
                image_size,
                conf_threshold,
            ],
            outputs=[output_image],
            cache_examples='lazy',
        )

gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv10: 实时端到端目标检测
    </h1>
    """)
    gr.HTML(
        """
        <h3 style='text-align: center'>
        <a href='https://github.com/YQisme/yolov10' target='_blank'>github</a>
        </h3>
        """)
    with gr.Row():
        with gr.Column():
            app()
if __name__ == '__main__':
    gradio_app.launch()