File size: 6,669 Bytes
3d9d465
 
 
 
 
 
 
 
7573e80
bb69e8f
7573e80
c9b6fea
 
 
 
 
 
 
 
 
 
3d9d465
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31638be
7573e80
c9b6fea
 
 
 
 
3d9d465
31638be
3d9d465
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd899bd
3d9d465
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31638be
3d9d465
 
 
 
 
31638be
3d9d465
 
 
59fdc3c
3d9d465
31638be
3d9d465
 
 
 
 
31638be
3d9d465
 
 
 
 
31638be
3d9d465
 
 
 
 
31638be
3d9d465
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd899bd
c6af47d
3d9d465
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
import numpy as np
import gradio as gr
from ultralytics import YOLO
import tempfile
import cv2

def inference(image, video, model_id, image_size, conf_threshold):
    if model_id == "yolov10n-obb":
        model = YOLO("pretrained/yolov10n-obb.pt")
    elif model_id == "yolov10s-640-obb":
        model = YOLO("pretrained/yolov10s-640-obb.pt")
    elif model_id == "yolov10s-obb":
        model = YOLO("pretrained/yolov10s-obb.pt")
    elif model_id == "yolov10m-obb":
        model = YOLO("pretrained/yolov10m-obb.pt")
    elif model_id == "yolov10b-obb":
        model = YOLO("pretrained/yolov10b-obb.pt")
    elif model_id == "yolov10l-obb":
        model = YOLO("pretrained/yolov10l-obb.pt")
    elif model_id == "yolov10x-obb":
        model = YOLO("pretrained/yolov10x-obb.pt")
    
    if image:
        results = model.predict(source=image, imgsz=image_size, conf=conf_threshold, device="cpu")
        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(*'vp90'), 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 inference_for_examples(image, model_path, image_size, conf_threshold):
    annotated_image, _ = 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="Input Type",
                )
                model_id = gr.Dropdown(
                    label="Model",
                    choices=[
                        "yolov10n-obb",
                        "yolov10s-640-obb",
                        "yolov10s-obb",
                        "yolov10m-obb",
                        "yolov10b-obb",
                        "yolov10l-obb",
                        "yolov10x-obb",
                    ],
                    value="yolov10n-obb",
                )
                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,
                )
                inferBtn = gr.Button(value="Detect")

            with gr.Column():
                output_image = gr.Image(type="numpy", label="Annotated Image", visible=True)
                output_video = gr.Video(label="Annotated Video", 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 inference(image, None, model_id, image_size, conf_threshold)
            else:
                return inference(None, video, model_id, image_size, conf_threshold)


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

        gr.Examples(
            examples=[
                [
                    "test_images/P0024.jpg",
                    "yolov10n-obb",
                    1024,
                    0.25,
                ],
                [
                    "test_images/P0035.jpg",
                    "yolov10n-obb",
                    1024,
                    0.25,
                ],
                [
                    "test_images/P0121.jpg",
                    "yolov10n-obb",
                    1024,
                    0.25,
                ],
                [
                    "test_images/P0180.jpg",
                    "yolov10n-obb",
                    1024,
                    0.25,
                ],
                [
                    "test_images/P0279.jpg",
                    "yolov10n-obb",
                    1024,
                    0.25,
                ],
                [
                    "test_images/P2112.jpg",
                    "yolov10n-obb",
                    1024,
                    0.25,
                ],               
            ],
            fn=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.Markdown(
        """
    # YOLOv10 - OBB (Oriented Bounding Box)

    for more detail description about this model, please visit [here](https://github.com/hamhanry/YOLOv10-OBB)
        """
    )
    with gr.Row():
        with gr.Column():
            app()
if __name__ == '__main__':
    gradio_app.queue()
    gradio_app.launch()