File size: 3,890 Bytes
d670799
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
_base_ = [
    '../../_base_/models/tsm_mobilenet_v2.py',
    '../../_base_/default_runtime.py'
]

# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data'
data_root_val = 'data'
ann_file_train = 'data/GenVidBench/label/fake_real_label/train.txt'
ann_file_val = 'data/GenVidBench/label/fake_real_label/test.txt'
ann_file_test = 'data/GenVidBench/label/fake_real_label/test.txt'

model = dict(cls_head=dict(num_classes=2))


file_client_args = dict(io_backend='disk')

train_pipeline = [
    dict(type='DecordInit', **file_client_args),
    dict(type='SampleFrames', clip_len=8, frame_interval=2, num_clips=1),
    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,
        num_fixed_crops=13),
    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=8,
        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', **file_client_args),
    dict(
        type='SampleFrames',
        clip_len=1,
        frame_interval=1,
        num_clips=8,
        test_mode=True),
    dict(type='DecordDecode'),
    dict(type='Resize', scale=(-1, 256)),
    dict(type='ThreeCrop', crop_size=256),
    dict(type='FormatShape', input_format='NCHW'),
    dict(type='PackActionInputs')
]

train_dataloader = dict(
    batch_size=16,
    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=16,
    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))
test_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,
        data_prefix=dict(video=data_root_val),
        pipeline=test_pipeline,
        test_mode=True))

val_evaluator = dict(type='AccMetric')
test_evaluator = val_evaluator

default_hooks = dict(checkpoint=dict(interval=3, max_keep_ckpts=3))

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(
    constructor='TSMOptimWrapperConstructor',
    paramwise_cfg=dict(fc_lr5=True),
    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.00002),
    clip_grad=dict(max_norm=20, norm_type=2))

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (16 samples per GPU).
auto_scale_lr = dict(enable=True, base_batch_size=128)