forked from open-mmlab/mmaction2
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtsn_r101_1x1x5_50e_mmit_rgb.py
115 lines (111 loc) · 3.5 KB
/
tsn_r101_1x1x5_50e_mmit_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
_base_ = [
'../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(
type='Recognizer2D',
backbone=dict(
type='ResNet',
pretrained='torchvision://resnet101',
depth=101,
norm_eval=False),
cls_head=dict(
type='TSNHead',
num_classes=313,
in_channels=2048,
spatial_type='avg',
consensus=dict(type='AvgConsensus', dim=1),
loss_cls=dict(type='BCELossWithLogits', loss_weight=160.0),
dropout_ratio=0.5,
init_std=0.01,
multi_class=True,
label_smooth_eps=0))
# model training and testing settings
train_cfg = None
test_cfg = dict(average_clips=None)
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/mmit/rawframes'
data_root_val = '/data/mmit/rawframes'
ann_file_train = 'data/mmit/mmit_train_rawframes.txt'
ann_file_val = 'data/mmit/mmit_val_rawframes.txt'
ann_file_test = 'data/mmit/mmit_val_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=1, frame_interval=1, num_clips=5),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=5,
test_mode=True),
dict(type='RawFrameDecode'),
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=5,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='MultiGroupCrop', crop_size=256, groups=1),
dict(type='Flip', flip_ratio=0),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=16,
workers_per_gpu=4,
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline,
multi_class=True,
num_classes=313),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline,
multi_class=True,
num_classes=313),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline,
multi_class=True,
num_classes=313))
evaluation = dict(interval=5, metrics=['mmit_mean_average_precision'])
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r101_1x1x5_50e_mmit_rgb/'