File size: 4,350 Bytes
68e3bf5
f4c379b
9e56ba5
 
 
 
 
 
5c10599
9e56ba5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96a688e
9e56ba5
 
 
 
 
 
 
 
 
 
 
359a44c
9e56ba5
 
 
 
 
 
 
 
 
 
 
f4c379b
 
 
 
 
9e56ba5
 
 
f4c379b
 
 
 
9e56ba5
f4c379b
9e56ba5
 
f4c379b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9e56ba5
f4c379b
9e56ba5
 
 
f4c379b
9e56ba5
f4c379b
9e56ba5
f4c379b
 
 
 
 
9e56ba5
 
f4c379b
9e56ba5
f4c379b
9e56ba5
f4c379b
 
 
 
 
 
 
 
 
 
9e56ba5
 
 
 
 
 
 
 
f4c379b
 
 
 
 
9e56ba5
 
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
import spaces
import gradio as gr
from detect_strongsort import run
import os
import threading

should_continue = True

@spaces.GPU(duration=60)
def yolov9_inference(model_id, image_size, conf_threshold, iou_threshold, img_path=None, vid_path=None):
    global should_continue
    img_extensions = ['.jpg', '.jpeg', '.png', '.gif']  # Add more image extensions if needed
    vid_extensions = ['.mp4', '.avi', '.mov', '.mkv']  # Add more video extensions if needed

    input_path = None
    if img_path is not None:
        _, img_extension = os.path.splitext(img_path)
        if img_extension.lower() in img_extensions:
            input_path = img_path
    elif vid_path is not None:
        _, vid_extension = os.path.splitext(vid_path)
        if vid_extension.lower() in vid_extensions:
            input_path = vid_path

    output_path = run(yolo_weights=model_id, imgsz=(image_size,image_size), conf_thres=conf_threshold, iou_thres=iou_threshold, source=input_path, device='0', strong_sort_weights = "osnet_x0_25_msmt17.pt", hide_conf= True)
    # Assuming output_path is the path to the output file
    _, output_extension = os.path.splitext(output_path)
    if output_extension.lower() in img_extensions:
        output_image = output_path  # Load the image file here
        output_video = None
    elif output_extension.lower() in vid_extensions:
        output_image = None
        output_video = output_path  # Load the video file here

    return output_image, output_video, output_path

@spaces.GPU(duration=60)
def inference(model_id, image_size, conf_threshold, iou_threshold, img_path=None, vid_path=None):
    global should_continue
    should_continue = True
    output_image, output_video, output_path = yolov9_inference(model_id, image_size, conf_threshold, iou_threshold, img_path, vid_path)
    return output_image, output_video, output_path


def stop_processing():
    global should_continue
    should_continue = False 
    return "Stop..."

def app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                gr.HTML("<h2>Input Parameters</h2>")
                img_path = gr.File(label="Image")
                vid_path = gr.File(label="Video")
                model_id = gr.Dropdown(
                    label="Model",
                    choices=[
                        "last_best_model.pt",
                        "best_model-converted.pt"
                    ],
                    value="./last_best_model.pt"
                    
                )
                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=0.4,
                )
                iou_threshold = gr.Slider(
                    label="IoU Threshold",
                    minimum=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.5,
                )
                yolov9_infer = gr.Button(value="Inference")
                stop_button = gr.Button(value="Stop")
            with gr.Column():
                gr.HTML("<h2>Output</h2>")
                output_image = gr.Image(type="numpy",label="Output Image")
                output_video = gr.Video(label="Output Video")
                output_path = gr.Textbox(label="Output path")

        yolov9_infer.click(
            fn=inference,
            inputs=[
                model_id,
                image_size,
                conf_threshold,
                iou_threshold,
                img_path,
                vid_path
            ],
            outputs=[output_image, output_video, output_path],
        )
        stop_button.click(stop_processing)


gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv9: Real-time Object Detection
    </h1>
    """)
    css = """
    body {
        background-color: #f0f0f0;
    }
    h1 {
        color: #4CAF50;
    }
    """
    with gr.Row():
        with gr.Column():
            app()

gradio_app.launch(debug=True)