Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
model.py 6.17 KB
Newer Older
limm's avatar
add test_mmagic and test_mmaction  
limm committed
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186 
# Copyright (c) OpenMMLab. All rights reserved.
model = dict(
    type='Recognizer2D',
    backbone=dict(
        type='ResNet',
        pretrained='https://download.pytorch.org/models/resnet50-11ad3fa6.pth',
        depth=50,
        norm_eval=False),
    cls_head=dict(
        type='TSNHead',
        num_classes=400,
        in_channels=2048,
        spatial_type='avg',
        consensus=dict(type='AvgConsensus', dim=1),
        dropout_ratio=0.4,
        init_std=0.01,
        average_clips=None),
    data_preprocessor=dict(
        type='ActionDataPreprocessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        format_shape='NCHW'),
    train_cfg=None,
    test_cfg=None)
train_cfg = dict(
    type='EpochBasedTrainLoop', max_epochs=100, val_begin=1, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [
    dict(
        type='MultiStepLR',
        begin=0,
        end=100,
        by_epoch=True,
        milestones=[40, 80],
        gamma=0.1)
]
optim_wrapper = dict(
    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001),
    clip_grad=dict(max_norm=40, norm_type=2))
default_scope = 'mmaction'
default_hooks = dict(
    runtime_info=dict(type='RuntimeInfoHook'),
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=20, ignore_last=False),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(
        type='CheckpointHook', interval=3, save_best='auto', max_keep_ckpts=3),
    sampler_seed=dict(type='DistSamplerSeedHook'))
env_cfg = dict(
    cudnn_benchmark=False,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True)
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')])
log_level = 'INFO'
load_from = None
resume = False
dataset_type = 'VideoDataset'
data_root = 'data/kinetics400/videos_train'
data_root_val = 'data/video'
ann_file_train = 'data/kinetics400/kinetics400_train_list_videos.txt'
ann_file_val = 'data/ann.txt'
train_pipeline = [
    dict(type='DecordInit'),
    dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=3),
    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'),
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=3,
        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')
]
test_pipeline = [
    dict(type='DecordInit'),
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=25,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='TenCrop', 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='VideoDataset',
        ann_file='data/kinetics400/kinetics400_train_list_videos.txt',
        data_prefix=dict(video='data/kinetics400/videos_train'),
        pipeline=[
            dict(type='DecordInit'),
            dict(
                type='SampleFrames', clip_len=1, frame_interval=1,
                num_clips=3),
            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_dataloader = dict(
    batch_size=32,
    num_workers=8,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='VideoDataset',
        ann_file='tests/test_codebase/test_mmaction/data/ann.txt',
        data_prefix=dict(video='tests/test_codebase/test_mmaction/data/video'),
        pipeline=[
            dict(type='DecordInit'),
            dict(
                type='SampleFrames',
                clip_len=1,
                frame_interval=1,
                num_clips=3,
                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')
        ],
        test_mode=True))
test_dataloader = dict(
    batch_size=1,
    num_workers=8,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='VideoDataset',
        ann_file='tests/test_codebase/test_mmaction/data/ann.txt',
        data_prefix=dict(video='tests/test_codebase/test_mmaction/data/video'),
        pipeline=[
            dict(type='DecordInit'),
            dict(
                type='SampleFrames',
                clip_len=1,
                frame_interval=1,
                num_clips=25,
                test_mode=True),
            dict(type='DecordDecode'),
            dict(type='Resize', scale=(-1, 256)),
            dict(type='TenCrop', crop_size=224),
            dict(type='FormatShape', input_format='NCHW'),
            dict(type='PackActionInputs')
        ],
        test_mode=True))
val_evaluator = dict(type='AccMetric')
test_evaluator = dict(type='AccMetric')