forked from open-mmlab/mmaction2
-
Notifications
You must be signed in to change notification settings - Fork 196
/
swin_small_patch244_window877_kinetics400_1k.py
122 lines (117 loc) · 3.83 KB
/
swin_small_patch244_window877_kinetics400_1k.py
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
_base_ = [
'../../_base_/models/swin/swin_small.py', '../../_base_/default_runtime.py'
]
model=dict(backbone=dict(patch_size=(2,4,4), drop_path_rate=0.1), test_cfg=dict(max_testing_views=4))
# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/kinetics400/train'
data_root_val = 'data/kinetics400/val'
ann_file_train = 'data/kinetics400/kinetics400_train_list.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='RandomResizedCrop'),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=32,
frame_interval=2,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Flip', flip_ratio=0),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=32,
frame_interval=2,
num_clips=4,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='ThreeCrop', crop_size=224),
dict(type='Flip', flip_ratio=0),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=4,
val_dataloader=dict(
videos_per_gpu=1,
workers_per_gpu=1
),
test_dataloader=dict(
videos_per_gpu=1,
workers_per_gpu=1
),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(type='AdamW', lr=1e-3, betas=(0.9, 0.999), weight_decay=0.02,
paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.),
'relative_position_bias_table': dict(decay_mult=0.),
'norm': dict(decay_mult=0.),
'backbone': dict(lr_mult=0.1)}))
# learning policy
lr_config = dict(
policy='CosineAnnealing',
min_lr=0,
warmup='linear',
warmup_by_epoch=True,
warmup_iters=2.5
)
total_epochs = 30
# runtime settings
checkpoint_config = dict(interval=1)
work_dir = './work_dirs/k400_swin_small_patch244_window877.py'
find_unused_parameters = False
# do not use mmdet version fp16
fp16 = None
optimizer_config = dict(
type="DistOptimizerHook",
update_interval=8,
grad_clip=None,
coalesce=True,
bucket_size_mb=-1,
use_fp16=True,
)