/
slowonly_r50_8xb16-4x16x1-256e_kinetics400-rgb.py
125 lines (110 loc) · 3.56 KB
/
slowonly_r50_8xb16-4x16x1-256e_kinetics400-rgb.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
123
124
125
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(pretrained=None))
# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/kinetics400/videos_train'
data_root_val = 'data/kinetics400/videos_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_videos.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_videos.txt'
file_client_args = dict(io_backend='disk')
train_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(type='SampleFrames', clip_len=4, frame_interval=16, 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='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
]
val_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
]
test_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
]
train_dataloader = dict(
batch_size=16,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=dict(video=data_root),
pipeline=train_pipeline))
val_dataloader = dict(
batch_size=16,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=dict(video=data_root_val),
pipeline=val_pipeline,
test_mode=True))
test_dataloader = dict(
batch_size=1,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=dict(video=data_root_val),
pipeline=test_pipeline,
test_mode=True))
val_evaluator = dict(type='AccMetric')
test_evaluator = val_evaluator
train_cfg = dict(
type='EpochBasedTrainLoop', max_epochs=256, val_begin=1, val_interval=5)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning policy
param_scheduler = [
dict(type='LinearLR', start_factor=0.1, by_epoch=True, begin=0, end=34),
dict(
type='CosineAnnealingLR',
T_max=222,
eta_min=0,
by_epoch=True,
begin=34,
end=256)
]
optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.2, momentum=0.9, weight_decay=1e-4),
clip_grad=dict(max_norm=40, norm_type=2))
# runtime settings
default_hooks = dict(checkpoint=dict(interval=4, max_keep_ckpts=3))
# 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)