File size: 5,847 Bytes
ea6c03c
 
 
 
808685d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
03c0240
5212d99
03c0240
 
5212d99
b86652f
 
 
5212d99
808685d
 
 
 
 
b86652f
 
808685d
 
 
 
 
 
 
 
 
d2a4be4
808685d
d2a4be4
808685d
 
 
 
 
 
 
 
 
 
 
 
5212d99
 
 
 
808685d
03c0240
 
 
 
 
 
 
 
3ccc6b5
03c0240
 
808685d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5212d99
808685d
 
 
 
 
 
3ccc6b5
808685d
 
 
 
 
 
 
 
b86652f
808685d
 
 
 
 
 
03c0240
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
import gradio as gr
from ultralytics import YOLOv10 
import supervision as sv
import spaces
from huggingface_hub import hf_hub_download

def download_models(model_id):
    hf_hub_download("kadirnar/Yolov10", filename=f"{model_id}", local_dir=f"./")
    return f"./{model_id}"
    
box_annotator = sv.BoxAnnotator()
category_dict = {
    0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus',
    6: 'train', 7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant',
    11: 'stop sign', 12: 'parking meter', 13: 'bench', 14: 'bird', 15: 'cat',
    16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear',
    22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag',
    27: 'tie', 28: 'suitcase', 29: 'frisbee', 30: 'skis', 31: 'snowboard',
    32: 'sports ball', 33: 'kite', 34: 'baseball bat', 35: 'baseball glove',
    36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle',
    40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl',
    46: 'banana', 47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli',
    51: 'carrot', 52: 'hot dog', 53: 'pizza', 54: 'donut', 55: 'cake',
    56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table',
    61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard',
    67: 'cell phone', 68: 'microwave', 69: 'oven', 70: 'toaster', 71: 'sink',
    72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors',
    77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush'
}

@spaces.GPU(duration=200)
def yolov10_inference(image, model_id, image_size, conf_threshold, iou_threshold):
    model_path = download_models(model_id)
    model = YOLOv10(model_path)
    results = model(source=image, imgsz=image_size, iou=iou_threshold, conf=conf_threshold, verbose=False)[0]
    detections = sv.Detections.from_ultralytics(results)
    
    labels = [
        f"{category_dict[class_id]} {confidence:.2f}"
        for class_id, confidence in zip(detections.class_id, detections.confidence)
    ]
    annotated_image = box_annotator.annotate(image, detections=detections, labels=labels)

    return annotated_image

def yolov10_inference_multi(image, image_size, conf_threshold, iou_threshold):
    yolov10n_image = yolov10_inference(image, "yolov10n.pt", image_size, conf_threshold, iou_threshold)
    yolov10s_image = yolov10_inference(image, "yolov10s.pt", image_size, conf_threshold, iou_threshold)
    yolov10m_image = yolov10_inference(image, "yolov10m.pt", image_size, conf_threshold, iou_threshold)
    yolov10b_image = yolov10_inference(image, "yolov10b.pt", image_size, conf_threshold, iou_threshold)
    yolov10l_image = yolov10_inference(image, "yolov10l.pt", image_size, conf_threshold, iou_threshold)
    yolov10x_image = yolov10_inference(image, "yolov10x.pt", image_size, conf_threshold, iou_threshold)
    return yolov10n_image, yolov10s_image, yolov10m_image, yolov10b_image, yolov10l_image, yolov10x_image

def app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                image = gr.Image(type="pil", label="Image")
                output_image_l = gr.Image(type="pil", label="yolov10l")
                output_image_x = gr.Image(type="pil", label="yolov10x")
                image_size = gr.Slider(
                    label="Image Size",
                    minimum=320,
                    maximum=1280,
                    step=32,
                    value=640,
                )
                conf_threshold = gr.Slider(
                    label="Confidence Threshold",
                    minimum=0.05,
                    maximum=1.0,
                    step=0.05,
                    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_n = gr.Image(type="pil", label="yolov10n")
                output_image_s = gr.Image(type="pil", label="yolov10s")
                output_image_m = gr.Image(type="pil", label="yolov10m")
                output_image_b = gr.Image(type="pil", label="yolov10b")

        yolov10_infer.click(
            fn=yolov10_inference_multi,
            inputs=[
                image,
                image_size,
                conf_threshold,
                iou_threshold,
            ],
            outputs=[output_image_n, output_image_s, output_image_m, output_image_b, output_image_l, output_image_x],
        )

        gr.Examples(
            examples=[
                [
                    "bridge_people.jpg",
                    640,
                    0.25,
                    0.45,
                ],
                [
                    "ships.jpg",
                    640,
                    0.25,
                    0.45,
                ],
                [
                    "dogs.jpg",
                    640,
                    0.25,
                    0.45,
                ],
            ],
            fn=yolov10_inference_multi,
            inputs=[
                image,
                image_size,
                conf_threshold,
                iou_threshold,
            ],
            outputs=[output_image_n, output_image_s, output_image_m, output_image_b, output_image_l, output_image_x],
            cache_examples=True,
        )

gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv10 - Comparison of Models
    </h1>
    """)
    with gr.Row():
        with gr.Column():
            app()

gradio_app.launch(debug=True)