| _base_ = [ | |
| '../../_base_/models/tpn_tsm_r50.py', '../../_base_/default_runtime.py' | |
| ] | |
| 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)) | |
| sthv1_flip_label_map = {2: 4, 4: 2, 30: 41, 41: 30, 52: 66, 66: 52} | |
| train_pipeline = [ | |
| dict(type='SampleFrames', clip_len=8, frame_interval=1, num_clips=1), | |
| dict(type='RawFrameDecode'), | |
| dict(type='RandomResizedCrop'), | |
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | |
| dict(type='Flip', flip_ratio=0.5, flip_label_map=sthv1_flip_label_map), | |
| dict(type='ColorJitter'), | |
| dict(type='FormatShape', input_format='NCHW'), | |
| dict(type='PackActionInputs') | |
| ] | |
| val_pipeline = [ | |
| dict( | |
| type='SampleFrames', | |
| clip_len=1, | |
| frame_interval=1, | |
| num_clips=8, | |
| test_mode=True), | |
| dict(type='RawFrameDecode'), | |
| 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='SampleFrames', | |
| clip_len=1, | |
| frame_interval=1, | |
| num_clips=8, | |
| twice_sample=True, | |
| test_mode=True), | |
| dict(type='RawFrameDecode'), | |
| 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=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(img=data_root), | |
| filename_tmpl='{:05}.jpg', | |
| 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(img=data_root_val), | |
| filename_tmpl='{:05}.jpg', | |
| 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(img=data_root_val), | |
| filename_tmpl='{:05}.jpg', | |
| pipeline=test_pipeline, | |
| test_mode=True)) | |
| val_evaluator = dict(type='AccMetric') | |
| test_evaluator = val_evaluator | |
| train_cfg = dict( | |
| type='EpochBasedTrainLoop', max_epochs=150, val_begin=1, val_interval=5) | |
| val_cfg = dict(type='ValLoop') | |
| test_cfg = dict(type='TestLoop') | |
| param_scheduler = [ | |
| dict( | |
| type='MultiStepLR', | |
| begin=0, | |
| end=150, | |
| by_epoch=True, | |
| milestones=[75, 125], | |
| gamma=0.1) | |
| ] | |
| optim_wrapper = dict( | |
| optimizer=dict( | |
| type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005, nesterov=True), | |
| clip_grad=dict(max_norm=20, norm_type=2)) | |