-
Notifications
You must be signed in to change notification settings - Fork 1.3k
/
Copy pathtsn_imagenet-pretrained-r50_8xb32-1x1x5-100e_kinetics400-rgb.py
63 lines (59 loc) · 1.94 KB
/
tsn_imagenet-pretrained-r50_8xb32-1x1x5-100e_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
_base_ = ['tsn_imagenet-pretrained-r50_8xb32-1x1x3-100e_kinetics400-rgb.py']
# 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=1, frame_interval=1, num_clips=5),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(
type='MultiScaleCrop',
input_size=224,
scales=(1, 0.875, 0.75, 0.66),
random_crop=False,
max_wh_scale_gap=1),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='FormatShape', input_format='NCHW'),
dict(type='PackActionInputs')
]
val_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=5,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='FormatShape', input_format='NCHW'),
dict(type='PackActionInputs')
]
train_dataloader = dict(
batch_size=32,
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=32,
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))