Hugging Face's logo

Spaces:
purkrmir
/
BBoxMaskPose-demo
Running on Zero

App Files Community
BBoxMaskPose-demo
File size: 2,838 Bytes 
a249588
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
_base_ = 'mmdet::rtmdet/rtmdet_l_8xb32-300e_coco.py'

input_shape = 320

model = dict(
    backbone=dict(
        deepen_factor=0.33,
        widen_factor=0.25,
        use_depthwise=True,
    ),
    neck=dict(
        in_channels=[64, 128, 256],
        out_channels=64,
        num_csp_blocks=1,
        use_depthwise=True,
    ),
    bbox_head=dict(
        in_channels=64,
        feat_channels=64,
        share_conv=False,
        exp_on_reg=False,
        use_depthwise=True,
        num_classes=1),
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.6),
        max_per_img=100))

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='CachedMosaic',
        img_scale=(input_shape, input_shape),
        pad_val=114.0,
        max_cached_images=20,
        random_pop=False),
    dict(
        type='RandomResize',
        scale=(input_shape * 2, input_shape * 2),
        ratio_range=(0.5, 1.5),
        keep_ratio=True),
    dict(type='RandomCrop', crop_size=(input_shape, input_shape)),
    dict(type='YOLOXHSVRandomAug'),
    dict(type='RandomFlip', prob=0.5),
    dict(
        type='Pad',
        size=(input_shape, input_shape),
        pad_val=dict(img=(114, 114, 114))),
    dict(type='PackDetInputs')
]

train_pipeline_stage2 = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='RandomResize',
        scale=(input_shape, input_shape),
        ratio_range=(0.5, 1.5),
        keep_ratio=True),
    dict(type='RandomCrop', crop_size=(input_shape, input_shape)),
    dict(type='YOLOXHSVRandomAug'),
    dict(type='RandomFlip', prob=0.5),
    dict(
        type='Pad',
        size=(input_shape, input_shape),
        pad_val=dict(img=(114, 114, 114))),
    dict(type='PackDetInputs')
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', scale=(input_shape, input_shape), keep_ratio=True),
    dict(
        type='Pad',
        size=(input_shape, input_shape),
        pad_val=dict(img=(114, 114, 114))),
    dict(
        type='PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                   'scale_factor'))
]

train_dataloader = dict(
    dataset=dict(pipeline=train_pipeline, metainfo=dict(classes=('person', ))))

val_dataloader = dict(
    dataset=dict(pipeline=test_pipeline, metainfo=dict(classes=('person', ))))
test_dataloader = val_dataloader

custom_hooks = [
    dict(
        type='EMAHook',
        ema_type='ExpMomentumEMA',
        momentum=0.0002,
        update_buffers=True,
        priority=49),
    dict(
        type='PipelineSwitchHook',
        switch_epoch=280,
        switch_pipeline=train_pipeline_stage2)
]