Hugging Face's logo

niobures
/
mmaction2

Model card Files
xet
Community
mmaction2
File size: 3,172 Bytes 
d3dbf03
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_ = 'mmaction::_base_/default_runtime.py'

custom_imports = dict(imports='models')

model = dict(
    type='RecognizerGCN',
    backbone=dict(
        type='CTRGCN', graph_cfg=dict(layout='coco', mode='spatial')),
    cls_head=dict(type='GCNHead', num_classes=60, in_channels=256))

dataset_type = 'PoseDataset'
ann_file = 'data/skeleton/ntu60_2d.pkl'
train_pipeline = [
    dict(type='PreNormalize2D'),
    dict(type='GenSkeFeat', dataset='coco', feats=['j']),
    dict(type='UniformSampleFrames', clip_len=100),
    dict(type='PoseDecode'),
    dict(type='FormatGCNInput', num_person=2),
    dict(type='PackActionInputs')
]
val_pipeline = [
    dict(type='PreNormalize2D'),
    dict(type='GenSkeFeat', dataset='coco', feats=['j']),
    dict(
        type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True),
    dict(type='PoseDecode'),
    dict(type='FormatGCNInput', num_person=2),
    dict(type='PackActionInputs')
]
test_pipeline = [
    dict(type='PreNormalize2D'),
    dict(type='GenSkeFeat', dataset='coco', feats=['j']),
    dict(
        type='UniformSampleFrames', clip_len=100, num_clips=10,
        test_mode=True),
    dict(type='PoseDecode'),
    dict(type='FormatGCNInput', num_person=2),
    dict(type='PackActionInputs')
]

train_dataloader = dict(
    batch_size=16,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type='RepeatDataset',
        times=5,
        dataset=dict(
            type=dataset_type,
            ann_file=ann_file,
            pipeline=train_pipeline,
            split='xsub_train')))
val_dataloader = dict(
    batch_size=16,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        ann_file=ann_file,
        pipeline=val_pipeline,
        split='xsub_val',
        test_mode=True))
test_dataloader = dict(
    batch_size=1,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        ann_file=ann_file,
        pipeline=test_pipeline,
        split='xsub_val',
        test_mode=True))

val_evaluator = [dict(type='AccMetric')]
test_evaluator = val_evaluator

train_cfg = dict(
    type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')

param_scheduler = [
    dict(
        type='CosineAnnealingLR',
        eta_min=0,
        T_max=16,
        by_epoch=True,
        convert_to_iter_based=True)
]

optim_wrapper = dict(
    optimizer=dict(
        type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True))

default_hooks = dict(checkpoint=dict(interval=1), logger=dict(interval=100))

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (16 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=128)