/
slowonly_k400-pre-r50_8xb8-8x8x1-10e_ava-kinetics-rgb.py
162 lines (147 loc) · 5.08 KB
/
slowonly_k400-pre-r50_8xb8-8x8x1-10e_ava-kinetics-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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
_base_ = '../../_base_/default_runtime.py'
url = ('https://download.openmmlab.com/mmaction/v1.0/recognition/slowonly/'
'slowonly_imagenet-pretrained-r50_8xb16-8x8x1-steplr-150e_kinetics400-'
'rgb/slowonly_imagenet-pretrained-r50_8xb16-8x8x1-steplr-150e_'
'kinetics400-rgb_20220901-df42dc84.pth')
model = dict(
type='FastRCNN',
_scope_='mmdet',
init_cfg=dict(type='Pretrained', checkpoint=url),
backbone=dict(
type='mmaction.ResNet3dSlowOnly',
depth=50,
pretrained=None,
pretrained2d=False,
lateral=False,
num_stages=4,
conv1_kernel=(1, 7, 7),
conv1_stride_t=1,
pool1_stride_t=1,
spatial_strides=(1, 2, 2, 1)),
roi_head=dict(
type='AVARoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor3D',
roi_layer_type='RoIAlign',
output_size=8,
with_temporal_pool=True),
bbox_head=dict(
type='BBoxHeadAVA',
background_class=True,
in_channels=2048,
num_classes=81,
multilabel=True,
dropout_ratio=0.5)),
data_preprocessor=dict(
type='mmaction.ActionDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
format_shape='NCTHW'),
train_cfg=dict(
rcnn=dict(
assigner=dict(
type='MaxIoUAssignerAVA',
pos_iou_thr=0.9,
neg_iou_thr=0.9,
min_pos_iou=0.9),
sampler=dict(
type='RandomSampler',
num=32,
pos_fraction=1,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=1.0)),
test_cfg=dict(rcnn=None))
dataset_type = 'AVAKineticsDataset'
data_root = 'data/ava_kinetics/rawframes'
anno_root = 'data/ava_kinetics/annotations'
ann_file_train = f'{anno_root}/ava_train_v2.2.csv'
ann_file_val = f'{anno_root}/ava_val_v2.2.csv'
exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.2.csv'
exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.2.csv'
label_file = f'{anno_root}/ava_action_list_v2.2_for_activitynet_2019.pbtxt'
proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
'recall_93.9.pkl')
proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
file_client_args = dict(io_backend='disk')
train_pipeline = [
dict(type='SampleAVAFrames', clip_len=8, frame_interval=8),
dict(type='RawFrameDecode', **file_client_args),
dict(type='RandomRescale', scale_range=(256, 320)),
dict(type='RandomCrop', size=256),
dict(type='Flip', flip_ratio=0.5),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='PackActionInputs')
]
# The testing is w/o. any cropping / flipping
val_pipeline = [
dict(type='SampleAVAFrames', clip_len=8, frame_interval=8, test_mode=True),
dict(type='RawFrameDecode', **file_client_args),
dict(type='Resize', scale=(-1, 256)),
dict(type='FormatShape', input_format='NCTHW', collapse=True),
dict(type='PackActionInputs')
]
train_dataloader = dict(
batch_size=8,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type=dataset_type,
ann_file=ann_file_train,
exclude_file=exclude_file_train,
pipeline=train_pipeline,
label_file=label_file,
proposal_file=proposal_file_train,
data_prefix=dict(img=data_root)))
val_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,
exclude_file=exclude_file_val,
pipeline=val_pipeline,
label_file=label_file,
proposal_file=proposal_file_val,
data_prefix=dict(img=data_root),
test_mode=True))
test_dataloader = val_dataloader
val_evaluator = dict(
type='AVAMetric',
ann_file=ann_file_val,
label_file=label_file,
exclude_file=exclude_file_val)
test_evaluator = val_evaluator
train_cfg = dict(
type='EpochBasedTrainLoop', max_epochs=10, val_begin=1, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [
dict(
type='LinearLR',
start_factor=0.1,
by_epoch=True,
begin=0,
end=2,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=8,
eta_min=0,
by_epoch=True,
begin=2,
end=10,
convert_to_iter_based=True)
]
optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.00001),
clip_grad=dict(max_norm=40, norm_type=2))
default_hooks = dict(checkpoint=dict(max_keep_ckpts=2))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (8 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=64)