|
|
_base_ = ['../../_base_/models/trn_r50.py', '../../_base_/default_runtime.py']
|
|
|
|
|
|
|
|
|
model = dict(cls_head=dict(num_classes=2))
|
|
|
|
|
|
|
|
|
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'
|
|
|
|
|
|
file_client_args = dict(io_backend='disk')
|
|
|
|
|
|
sthv2_flip_label_map = {86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166}
|
|
|
train_pipeline = [
|
|
|
dict(type='DecordInit', **file_client_args),
|
|
|
dict(type='SampleFrames', clip_len=8, frame_interval=1, 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, flip_label_map=sthv2_flip_label_map),
|
|
|
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,
|
|
|
twice_sample=True,
|
|
|
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
|
|
|
|
|
|
train_cfg = dict(
|
|
|
type='EpochBasedTrainLoop', max_epochs=50, val_begin=1, val_interval=1)
|
|
|
val_cfg = dict(type='ValLoop')
|
|
|
test_cfg = dict(type='TestLoop')
|
|
|
|
|
|
optim_wrapper = dict(
|
|
|
constructor='TSMOptimWrapperConstructor',
|
|
|
paramwise_cfg=dict(fc_lr5=False),
|
|
|
optimizer=dict(type='SGD', lr=0.002, momentum=0.9, weight_decay=5e-4),
|
|
|
clip_grad=dict(max_norm=20, norm_type=2))
|
|
|
|
|
|
param_scheduler = [
|
|
|
dict(
|
|
|
type='MultiStepLR',
|
|
|
begin=0,
|
|
|
end=50,
|
|
|
by_epoch=True,
|
|
|
milestones=[30, 45],
|
|
|
gamma=0.1)
|
|
|
]
|
|
|
|
|
|
default_hooks = dict(checkpoint=dict(max_keep_ckpts=3))
|
|
|
|
|
|
find_unused_parameters = True
|
|
|
|
