|
|
custom_imports = dict(imports='models')
|
|
|
|
|
|
|
|
|
model = dict(
|
|
|
type='Recognizer3D',
|
|
|
backbone=dict(
|
|
|
type='UMTViT',
|
|
|
patch_size=16,
|
|
|
embed_dim=1024,
|
|
|
depth=24,
|
|
|
num_heads=16,
|
|
|
mlp_ratio=4,
|
|
|
all_frames=8,
|
|
|
qkv_bias=True),
|
|
|
cls_head=dict(
|
|
|
type='TimeSformerHead',
|
|
|
num_classes=400,
|
|
|
in_channels=1024,
|
|
|
average_clips='prob'),
|
|
|
data_preprocessor=dict(
|
|
|
type='ActionDataPreprocessor',
|
|
|
mean=[114.75, 114.75, 114.75],
|
|
|
std=[57.375, 57.375, 57.375],
|
|
|
format_shape='NCTHW'))
|
|
|
|
|
|
|
|
|
dataset_type = 'VideoDataset'
|
|
|
data_root_val = 'data/kinetics400/videos_val'
|
|
|
ann_file_test = 'data/kinetics400/kinetics400_val_list_videos.txt'
|
|
|
|
|
|
file_client_args = dict(io_backend='disk')
|
|
|
|
|
|
test_pipeline = [
|
|
|
dict(type='DecordInit', **file_client_args),
|
|
|
dict(type='UniformSample', clip_len=8, 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')
|
|
|
]
|
|
|
|
|
|
test_dataloader = dict(
|
|
|
batch_size=8,
|
|
|
num_workers=16,
|
|
|
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))
|
|
|
|
|
|
test_evaluator = dict(type='AccMetric')
|
|
|
test_cfg = dict(type='TestLoop')
|
|
|
|
|
|
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=1, save_best='auto', max_keep_ckpts=5),
|
|
|
sampler_seed=dict(type='DistSamplerSeedHook'),
|
|
|
sync_buffers=dict(type='SyncBuffersHook'))
|
|
|
|
|
|
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=vis_backends)
|
|
|
|
|
|
log_level = 'INFO'
|
|
|
load_from = None
|
|
|
resume = False
|
|
|
|
