File size: 5,032 Bytes
79d95c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be5235d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79d95c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22a7b4d
79d95c0
9968e5d
79d95c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d9354b
79d95c0
 
22a7b4d
79d95c0
 
 
 
0d9354b
79d95c0
 
22a7b4d
79d95c0
 
 
0d9354b
79d95c0
 
22a7b4d
79d95c0
 
 
 
 
 
 
 
 
 
 
d8b991d
79d95c0
 
 
 
 
 
 
30e4b6a
79d95c0
30e4b6a
 
ee8ac98
 
 
 
 
 
79d95c0
 
 
 
 
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
import spaces
import supervision as sv
import PIL.Image as Image
from ultralytics import YOLO
import gradio as gr
import torch



model_filenames = [
    "yolo11n.pt", 
    "yolo11s.pt",
    "yolo11m.pt", 
    "yolo11l.pt", 
    "yolo11x.pt"
]



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
def yolo_inference(image, model_id, conf_threshold, iou_threshold, max_detection):

    
    model = YOLO(model_id)
    results = model(source=image, imgsz=640, iou=iou_threshold, conf=conf_threshold, verbose=False, max_det=max_detection)[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 app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                image = gr.Image(type="pil", label="Image", interactive=True)
    
                model_id = gr.Dropdown(
                    label="Model",
                    choices=model_filenames,
                    value=model_filenames[0] if model_filenames else "",
                )
                conf_threshold = gr.Slider(
                    label="Confidence Threshold",
                    minimum=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.25,
                )
                iou_threshold = gr.Slider(
                    label="IoU Threshold",
                    minimum=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.45,
                )
                
                max_detection = gr.Slider(
                    label="Max Detection",
                    minimum=1,
                    maximum=300,
                    step=1,
                    value=300,
                )
                yolov_infer = gr.Button(value="Detect Objects")

            with gr.Column():
                output_image = gr.Image(type="pil", label="Annotated Image", interactive=False)

        yolov_infer.click(
            fn=yolo_inference,
            inputs=[
                image,
                model_id,
                conf_threshold,
                iou_threshold,
                max_detection,
            ],
            outputs=[output_image],
        )

        gr.Examples(
            examples=[
                [
                    "zidane.jpg",
                    "yolo11s.pt",
                    0.25,
                    0.45,
                    300,
                ],
                
                [
                    "bus.jpg",
                    "yolo11m.pt",
                    0.25,
                    0.45,
                    300,
                ],
                [
                    "yolo_vision.jpg",
                    "yolo11x.pt",
                    0.25,
                    0.45,
                    300,
                ],
            ],
            fn=yolo_inference,
            inputs=[
                image,
                model_id,
                conf_threshold,
                iou_threshold,
                max_detection,
            ],
            outputs=[output_image],
            cache_examples=True,
        )

gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    Yolo11: Object Detection
    </h1>
        <a>
        """)
    gr.HTML(
    """
    <p style='text-align: center'>
    Latest ultralytics yolo11 object detection models. Upload an image to run inference.
    </p>
    """)
    with gr.Row():
        with gr.Column():
            app()

gradio_app.launch()