File size: 4,273 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 |
_base_ = [
'../../_base_/models/swin_tiny.py', '../../_base_/default_runtime.py'
]
model = dict(
backbone=dict(
pretrained= # noqa: E251
'https://download.openmmlab.com/mmaction/v1.0/recognition/swin/swin_tiny_patch4_window7_224.pth' # noqa: E501
))
# 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='RandomResizedCrop'),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
]
val_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='SampleFrames',
clip_len=32,
frame_interval=2,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
]
test_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='SampleFrames',
clip_len=32,
frame_interval=2,
num_clips=4,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='ThreeCrop', crop_size=224),
dict(type='FormatShape', input_format='NCTHW'),
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,
data_prefix=dict(video=data_root),
pipeline=train_pipeline))
val_dataloader = dict(
batch_size=8,
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_test,
data_prefix=dict(video=data_root_val),
pipeline=test_pipeline,
test_mode=True))
val_evaluator = dict(type='AccMetric')
test_evaluator = val_evaluator
train_cfg = dict(
type='EpochBasedTrainLoop', max_epochs=30, val_begin=1, val_interval=3)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
optim_wrapper = dict(
type='AmpOptimWrapper',
optimizer=dict(
type='AdamW', lr=1e-3, betas=(0.9, 0.999), weight_decay=0.02),
constructor='SwinOptimWrapperConstructor',
paramwise_cfg=dict(
absolute_pos_embed=dict(decay_mult=0.),
relative_position_bias_table=dict(decay_mult=0.),
norm=dict(decay_mult=0.),
backbone=dict(lr_mult=0.1)))
param_scheduler = [
dict(
type='LinearLR',
start_factor=0.1,
by_epoch=True,
begin=0,
end=2.5,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=30,
eta_min=0,
by_epoch=True,
begin=0,
end=30)
]
default_hooks = dict(
checkpoint=dict(interval=3, max_keep_ckpts=5), logger=dict(interval=100))
# 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)
|