forked from open-mmlab/mmaction2
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathi3d_r50_lazy_32x2x1_100e_kinetics400_rgb.py
84 lines (82 loc) · 2.88 KB
/
i3d_r50_lazy_32x2x1_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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
_base_ = ['./i3d_r50_32x2x1_100e_kinetics400_rgb.py']
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.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='SampleFrames', clip_len=32, frame_interval=2, num_clips=1),
dict(type='RawFrameDecode', decoding_backend='turbojpeg'),
dict(type='Resize', scale=(-1, 256), lazy=True),
dict(
type='MultiScaleCrop',
input_size=224,
scales=(1, 0.8),
random_crop=False,
max_wh_scale_gap=0,
lazy=True),
dict(type='Resize', scale=(224, 224), keep_ratio=False, lazy=True),
dict(type='Flip', flip_ratio=0.5, lazy=True),
dict(type='Fuse'),
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='SampleFrames',
clip_len=32,
frame_interval=2,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode', decoding_backend='turbojpeg'),
dict(type='Resize', scale=(-1, 256), lazy=True),
dict(type='CenterCrop', crop_size=224, lazy=True),
dict(type='Flip', flip_ratio=0, lazy=True),
dict(type='Fuse'),
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='SampleFrames',
clip_len=32,
frame_interval=2,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode', decoding_backend='turbojpeg'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
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,
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_val,
data_prefix=data_root_val,
pipeline=test_pipeline))
# runtime settings
work_dir = './work_dirs/i3d_r50_lazy_32x2x1_100e_kinetics400_rgb/'