Skip to content

GitLab

Commit 37437e80 authored by sunxx1's avatar sunxx1
Browse files

Merge branch 'sun_22.10' into 'main' 

Sun 22.10

See merge request dcutoolkit/deeplearing/dlexamples_new!54
parents 8442f072 701c0060
Hide whitespace changes
Inline Side-by-side
Showing with 1692 additions and 0 deletions
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_k400_pretrained_r50_8x4x1_40e_hmdb51_rgb.py 0 → 100644
View file @ 37437e80
_base_ = ['./slowonly_k400_pretrained_r50_8x4x1_40e_ucf101_rgb.py']
# model settings
model = dict(cls_head=dict(num_classes=51))
# dataset settings
split = 1
dataset_type = 'RawframeDataset'
data_root = 'data/hmdb51/rawframes'
data_root_val = 'data/hmdb51/rawframes'
ann_file_train = f'data/hmdb51/hmdb51_train_split_{split}_rawframes.txt'
ann_file_val = f'data/hmdb51/hmdb51_val_split_{split}_rawframes.txt'
ann_file_test = f'data/hmdb51/hmdb51_val_split_{split}_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=4,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=4,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
# runtime settings
work_dir = './work_dirs/slowonly_k400_pretrained_r50_8x4x1_40e_hmdb51_rgb'
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_k400_pretrained_r50_8x4x1_40e_ucf101_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/schedules/sgd_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=101))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/ucf101/rawframes/'
data_root_val = 'data/ucf101/rawframes/'
split = 1 # official train/test splits. valid numbers: 1, 2, 3
ann_file_train = f'data/ucf101/ucf101_train_split_{split}_rawframes.txt'
ann_file_val = f'data/ucf101/ucf101_val_split_{split}_rawframes.txt'
ann_file_test = f'data/ucf101/ucf101_val_split_{split}_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=4,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=4,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
lr=0.001, # this lr is used for 8 gpus
)
optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[15, 30])
total_epochs = 40
# runtime settings
work_dir = './work_dirs/slowonly_k400_pretrained_r50_8x4x1_40e_ucf101_rgb'
load_from = 'https://download.openmmlab.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8x1_256e_kinetics400_rgb_20200703-a79c555a.pth' # noqa: E501
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py',
'../../_base_/schedules/sgd_150e_warmup.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(
backbone=dict(
non_local=((0, 0, 0), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 0, 0)),
non_local_cfg=dict(
sub_sample=True,
use_scale=True,
norm_cfg=dict(type='BN3d', requires_grad=True),
mode='embedded_gaussian')))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=4, frame_interval=16, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# runtime settings
work_dir = './work_dirs/slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb' # noqa E501
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_nl_embedded_gaussian_r50_8x8x1_150e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py',
'../../_base_/schedules/sgd_150e_warmup.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(
backbone=dict(
non_local=((0, 0, 0), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 0, 0)),
non_local_cfg=dict(
sub_sample=True,
use_scale=True,
norm_cfg=dict(type='BN3d', requires_grad=True),
mode='embedded_gaussian')))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.01, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
# runtime settings
work_dir = './work_dirs/slowonly_nl_embedded_gaussian_r50_8x8x1_150e_kinetics400_rgb' # noqa E501
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r101_8x8x1_196e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = ['./slowonly_r50_8x8x1_256e_kinetics400_rgb.py']
# model settings
model = dict(backbone=dict(depth=101, pretrained=None))
# optimizer
optimizer = dict(
type='SGD', lr=0.1, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
# learning policy
lr_config = dict(
policy='CosineAnnealing',
min_lr=0,
warmup='linear',
warmup_ratio=0.1,
warmup_by_epoch=True,
warmup_iters=34)
total_epochs = 196
# runtime settings
work_dir = './work_dirs/slowonly_r101_8x8x1_196e_kinetics400_rgb'
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(in_channels=2, with_pool2=False))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics_flow_train_list.txt'
ann_file_val = 'data/kinetics400/kinetics_flow_val_list.txt'
ann_file_test = 'data/kinetics400/kinetics_flow_val_list.txt'
img_norm_cfg = dict(mean=[128, 128], std=[128, 128])
train_pipeline = [
dict(type='SampleFrames', clip_len=4, frame_interval=16, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=24,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
modality='Flow',
filename_tmpl='{}_{:05d}.jpg',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
modality='Flow',
filename_tmpl='{}_{:05d}.jpg',
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
modality='Flow',
filename_tmpl='{}_{:05d}.jpg',
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.06, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(
policy='CosineAnnealing',
min_lr=0,
warmup='linear',
warmup_by_epoch=True,
warmup_iters=34)
total_epochs = 256
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_4x16x1_256e_kinetics400_flow'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(pretrained=None))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=4, frame_interval=16, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.1, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0)
total_epochs = 256
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_4x16x1_256e_kinetics400_rgb'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(in_channels=2, with_pool2=False))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics_flow_train_list.txt'
ann_file_val = 'data/kinetics400/kinetics_flow_val_list.txt'
ann_file_test = 'data/kinetics400/kinetics_flow_val_list.txt'
img_norm_cfg = dict(mean=[128, 128], std=[128, 128])
train_pipeline = [
dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=12,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
modality='Flow',
filename_tmpl='{}_{:05d}.jpg',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
modality='Flow',
filename_tmpl='{}_{:05d}.jpg',
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
modality='Flow',
filename_tmpl='{}_{:05d}.jpg',
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.06, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(
policy='CosineAnnealing',
min_lr=0,
warmup='linear',
warmup_by_epoch=True,
warmup_iters=34)
total_epochs = 196
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_8x8x1_256e_kinetics400_flow'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(pretrained=None))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=1,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=10,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.1, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0)
total_epochs = 256
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_8x8x1_256e_kinetics400_rgb'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_clip_feature_extraction_4x16x1_rgb.py 0 → 100644
View file @ 37437e80
model = dict(
type='Recognizer3D',
backbone=dict(
type='ResNet3dSlowOnly',
depth=50,
pretrained=None,
lateral=False,
conv1_kernel=(1, 7, 7),
conv1_stride_t=1,
pool1_stride_t=1,
inflate=(0, 0, 1, 1),
norm_eval=False),
train_cfg=None,
test_cfg=dict(feature_extraction=True))
# dataset settings
dataset_type = 'VideoDataset'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=1,
workers_per_gpu=2,
test=dict(
type=dataset_type,
ann_file=None,
data_prefix=None,
pipeline=test_pipeline))
dist_params = dict(backend='nccl')
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(pretrained=None))
# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/kinetics400/videos_train'
data_root_val = 'data/kinetics400/videos_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_videos.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_videos.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_videos.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=4, frame_interval=16, 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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=24,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.3, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0)
total_epochs = 256
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_video_4x16x1_256e_kinetics400_rgb'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_video_8x8x1_256e_kinetics600_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(pretrained=None), cls_head=dict(num_classes=600))
# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/kinetics600/videos_train'
data_root_val = 'data/kinetics600/videos_val'
ann_file_train = 'data/kinetics600/kinetics600_train_list_videos.txt'
ann_file_val = 'data/kinetics600/kinetics600_val_list_videos.txt'
ann_file_test = 'data/kinetics600/kinetics600_val_list_videos.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1),
dict(type='DecordDecode'),
dict(type='RandomResizedCrop'),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=10,
test_mode=True),
dict(type='DecordDecode'),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=12,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.15, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0)
total_epochs = 256
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_video_8x8x1_256e_kinetics600_rgb'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_video_8x8x1_256e_kinetics700_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/slowonly_r50.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(pretrained=None), cls_head=dict(num_classes=700))
dataset_type = 'VideoDataset'
data_root = 'data/kinetics700/videos_train'
data_root_val = 'data/kinetics700/videos_val'
ann_file_train = 'data/kinetics700/kinetics700_train_list_videos.txt'
ann_file_val = 'data/kinetics700/kinetics700_val_list_videos.txt'
ann_file_test = 'data/kinetics700/kinetics700_val_list_videos.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1),
dict(type='DecordDecode'),
dict(type='RandomResizedCrop'),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=8,
frame_interval=8,
num_clips=10,
test_mode=True),
dict(type='DecordDecode'),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=12,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.15, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
# learning policy
lr_config = dict(policy='CosineAnnealing', min_lr=0)
total_epochs = 256
# runtime settings
checkpoint_config = dict(interval=4)
work_dir = './work_dirs/slowonly_r50_video_8x8x1_256e_kinetics700_rgb'
find_unused_parameters = False
openmmlab_test/mmaction2-0.24.1/configs/recognition/slowonly/slowonly_r50_video_inference_4x16x1_256e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = ['../../_base_/models/slowonly_r50.py']
# model settings
model = dict(backbone=dict(pretrained=None))
# dataset settings
dataset_type = 'VideoDataset'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=4,
frame_interval=16,
num_clips=10,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='Collect', keys=['imgs'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=1,
workers_per_gpu=2,
test=dict(
type=dataset_type,
ann_file=None,
data_prefix=None,
pipeline=test_pipeline))
openmmlab_test/mmaction2-0.24.1/configs/recognition/tanet/README.md 0 → 100644
View file @ 37437e80
# TANet
[TAM: Temporal Adaptive Module for Video Recognition](https://openaccess.thecvf.com/content/ICCV2021/html/Liu_TAM_Temporal_Adaptive_Module_for_Video_Recognition_ICCV_2021_paper.html)
<!-- [ALGORITHM] -->
## Abstract
<!-- [ABSTRACT] -->
Video data is with complex temporal dynamics due to various factors such as camera motion, speed variation, and different activities. To effectively capture this diverse motion pattern, this paper presents a new temporal adaptive module ({\\bf TAM}) to generate video-specific temporal kernels based on its own feature map. TAM proposes a unique two-level adaptive modeling scheme by decoupling the dynamic kernel into a location sensitive importance map and a location invariant aggregation weight. The importance map is learned in a local temporal window to capture short-term information, while the aggregation weight is generated from a global view with a focus on long-term structure. TAM is a modular block and could be integrated into 2D CNNs to yield a powerful video architecture (TANet) with a very small extra computational cost. The extensive experiments on Kinetics-400 and Something-Something datasets demonstrate that our TAM outperforms other temporal modeling methods consistently, and achieves the state-of-the-art performance under the similar complexity.
<!-- [IMAGE] -->
<div align=center>
<img src="https://user-images.githubusercontent.com/34324155/143018253-c3e1ba5b-ac35-4c55-be28-0134b76888e8.png" width="800"/>
</div>
## Results and Models
### Kinetics-400
| config | resolution | gpus | backbone | pretrain | top1 acc | top5 acc | reference top1 acc | reference top5 acc | inference_time(video/s) | gpu_mem(M) | ckpt | log | json |
| :--------------------------------------------------------------------------------------------------------------------- | :------------: | :--: | :------: | :------: | :------: | :------: | :----------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: | :---------------------: | :--------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [tanet_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py) | short-side 320 | 8 | TANet | ImageNet | 76.28 | 92.60 | [76.22](https://github.com/liu-zhy/temporal-adaptive-module/blob/master/scripts/test_tam_kinetics_rgb_8f.sh) | [92.53](https://github.com/liu-zhy/temporal-adaptive-module/blob/master/scripts/test_tam_kinetics_rgb_8f.sh) | x | 7124 | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219-032c8e94.pth) | [log](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219.log) | [json](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219.json) |
### Something-Something V1
| config | resolution | gpus | backbone | pretrain | top1 acc (efficient/accurate) | top5 acc (efficient/accurate) | gpu_mem(M) | ckpt | log | json |
| :--------------------------------------------------------------------------------------------- | :--------: | :--: | :------: | :------: | :---------------------------: | :---------------------------: | :--------: | :---------------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------: |
| [tanet_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb.py) | height 100 | 8 | TANet | ImageNet | 47.34/49.58 | 75.72/77.31 | 7127 | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/tanet_r50_1x1x8_50e_sthv1_rgb_20210630-f4a48609.pth) | [log](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/20210606_205006.log) | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/20210606_205006.log.json) |
| [tanet_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb.py) | height 100 | 8 | TANet | ImageNet | 49.05/50.91 | 77.90/79.13 | 7127 | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb_20211202-370c2128.pth) | [log](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb.log) | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb.json) |
:::{note}
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 8 GPUs x 8 videos/gpu and lr=0.04 for 16 GPUs x 16 videos/gpu.
2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time, not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
3. The values in columns named after "reference" are the results got by testing on our dataset, using the checkpoints provided by the author with same model settings. The checkpoints for reference repo can be downloaded [here](https://drive.google.com/drive/folders/1sFfmP3yrfc7IzRshEELOby7-aEoymIFL?usp=sharing).
4. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
:::
For more details on data preparation, you can refer to corresponding parts in [Data Preparation](/docs/data_preparation.md).
## Train
You can use the following command to train a model.
```shell
python tools/train.py ${CONFIG_FILE} [optional arguments]
```
Example: train TANet model on Kinetics-400 dataset in a deterministic option with periodic validation.
```shell
python tools/train.py configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py \
--work-dir work_dirs/tanet_r50_dense_1x1x8_100e_kinetics400_rgb \
--validate --seed 0 --deterministic
```
For more details, you can refer to **Training setting** part in [getting_started](/docs/getting_started.md#training-setting).
## Test
You can use the following command to test a model.
```shell
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
```
Example: test TANet model on Kinetics-400 dataset and dump the result to a json file.
```shell
python tools/test.py configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py \
checkpoints/SOME_CHECKPOINT.pth --eval top_k_accuracy mean_class_accuracy \
--out result.json
```
For more details, you can refer to **Test a dataset** part in [getting_started](/docs/getting_started.md#test-a-dataset).
## Citation
```BibTeX
@article{liu2020tam,
title={TAM: Temporal Adaptive Module for Video Recognition},
author={Liu, Zhaoyang and Wang, Limin and Wu, Wayne and Qian, Chen and Lu, Tong},
journal={arXiv preprint arXiv:2005.06803},
year={2020}
}
```
openmmlab_test/mmaction2-0.24.1/configs/recognition/tanet/README_zh-CN.md 0 → 100644
View file @ 37437e80
# TANet
## 简介
<!-- [ALGORITHM] -->
```BibTeX
@article{liu2020tam,
title={TAM: Temporal Adaptive Module for Video Recognition},
author={Liu, Zhaoyang and Wang, Limin and Wu, Wayne and Qian, Chen and Lu, Tong},
journal={arXiv preprint arXiv:2005.06803},
year={2020}
}
```
## 模型库
### Kinetics-400
| 配置文件 | 分辨率 | GPU 数量 | 主干网络 | 预训练 | top1 准确率 | top5 准确率 | 参考代码的 top1 准确率 | 参考代码的 top5 准确率 | 推理时间 (video/s) | GPU 显存占用 (M) | ckpt | log | json |
| :--------------------------------------------------------------------------------------------------------------------- | :------: | :------: | :------: | :------: | :---------: | :---------: | :----------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: | :----------------: | :--------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [tanet_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py) | 短边 320 | 8 | TANet | ImageNet | 76.28 | 92.60 | [76.22](https://github.com/liu-zhy/temporal-adaptive-module/blob/master/scripts/test_tam_kinetics_rgb_8f.sh) | [92.53](https://github.com/liu-zhy/temporal-adaptive-module/blob/master/scripts/test_tam_kinetics_rgb_8f.sh) | x | 7124 | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219-032c8e94.pth) | [log](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219.log) | [json](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219.json) |
### Something-Something V1
| 配置文件 | 分辨率 | GPU 数量 | 主干网络 | 预训练 | top1 准确率 (efficient/accurate) | top5 准确率 (efficient/accurate) | GPU 显存占用 (M) | ckpt | log | json |
| :--------------------------------------------------------------------------------------------- | :----: | :------: | :------: | :------: | :------------------------------: | :------------------------------: | :--------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------: |
| [tanet_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb.py) | 高 100 | 8 | TANet | ImageNet | 47.34/49.58 | 75.72/77.31 | 7127 | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/tanet_r50_1x1x8_50e_sthv1_rgb_20210630-f4a48609.pth) | [log](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/20210606_205006.log) | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/20210606_205006.log.json) |
| [tanet_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb.py) | 高 100 | 8 | TANet | ImageNet | 49.05/50.91 | 77.90/79.13 | 7127 | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb_20211202-370c2128.pth) | [log](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb.log) | [ckpt](https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb.json) |
注：
1. 这里的 **GPU 数量** 指的是得到模型权重文件对应的 GPU 个数。默认地，MMAction2 所提供的配置文件对应使用 8 块 GPU 进行训练的情况。
依据 [线性缩放规则](https://arxiv.org/abs/1706.02677)，当用户使用不同数量的 GPU 或者每块 GPU 处理不同视频个数时，需要根据批大小等比例地调节学习率。
如，lr=0.01 对应 4 GPUs x 2 video/gpu，以及 lr=0.08 对应 16 GPUs x 4 video/gpu。
2. 这里的 **推理时间** 是根据 [基准测试脚本](/tools/analysis/benchmark.py) 获得的，采用测试时的采帧策略，且只考虑模型的推理时间，
并不包括 IO 时间以及预处理时间。对于每个配置，MMAction2 使用 1 块 GPU 并设置批大小（每块 GPU 处理的视频个数）为 1 来计算推理时间。
3. 参考代码的结果是通过使用相同的模型配置在原来的代码库上训练得到的。对应的模型权重文件可从 [这里](https://drive.google.com/drive/folders/1sFfmP3yrfc7IzRshEELOby7-aEoymIFL?usp=sharing) 下载。
4. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
对于数据集准备的细节，用户可参考 [数据集准备文档](/docs_zh_CN/data_preparation.md) 中的 Kinetics400 部分。
## 如何训练
用户可以使用以下指令进行模型训练。
```shell
python tools/train.py ${CONFIG_FILE} [optional arguments]
```
例如：以一个确定性的训练方式，辅以定期的验证过程进行 TANet 模型在 Kinetics400 数据集上的训练。
```shell
python tools/train.py configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py \
--work-dir work_dirs/tanet_r50_dense_1x1x8_100e_kinetics400_rgb \
--validate --seed 0 --deterministic
```
更多训练细节，可参考 [基础教程](/docs_zh_CN/getting_started.md#%E8%AE%AD%E7%BB%83%E9%85%8D%E7%BD%AE) 中的 **训练配置** 部分。
## 如何测试
用户可以使用以下指令进行模型测试。
```shell
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
```
例如：在 Kinetics400 数据集上测试 TANet 模型，并将结果导出为一个 json 文件。
```shell
python tools/test.py configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py \
checkpoints/SOME_CHECKPOINT.pth --eval top_k_accuracy mean_class_accuracy \
--out result.json
```
更多测试细节，可参考 [基础教程](/docs_zh_CN/getting_started.md#%E6%B5%8B%E8%AF%95%E6%9F%90%E4%B8%AA%E6%95%B0%E6%8D%AE%E9%9B%86) 中的 **测试某个数据集** 部分。
openmmlab_test/mmaction2-0.24.1/configs/recognition/tanet/metafile.yml 0 → 100644
View file @ 37437e80
Collections:
- Name: TANet
README: configs/recognition/tanet/README.md
Paper:
URL: https://arxiv.org/abs/2005.06803
Title: "TAM: Temporal Adaptive Module for Video Recognition"
Models:
- Config: configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py
In Collection: TANet
Metadata:
Architecture: TANet
Batch Size: 8
Epochs: 100
FLOPs: 43065983104
Parameters: 25590320
Pretrained: ImageNet
Resolution: short-side 320
Training Data: Kinetics-400
Training Resources: 8 GPUs
Modality: RGB
Name: tanet_r50_dense_1x1x8_100e_kinetics400_rgb
Results:
- Dataset: Kinetics-400
Metrics:
Top 1 Accuracy: 76.28
Top 5 Accuracy: 92.6
Task: Action Recognition
Training Json Log: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219.json
Training Log: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219.log
Weights: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/tanet_r50_dense_1x1x8_100e_kinetics400_rgb_20210219-032c8e94.pth
- Config: configs/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb.py
In Collection: TANet
Metadata:
Architecture: TANet
Batch Size: 8
Epochs: 50
FLOPs: 32972787840
Parameters: 25127246
Pretrained: ImageNet
Resolution: height 100
Training Data: SthV1
Training Resources: 8 GPUs
Modality: RGB
Name: tanet_r50_1x1x8_50e_sthv1_rgb
Results:
- Dataset: SthV1
Metrics:
Top 1 Accuracy: 49.58
Top 1 Accuracy (efficient): 47.34
Top 5 Accuracy: 77.31
Top 5 Accuracy (efficient): 75.72
Task: Action Recognition
Training Json Log: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/20210606_205006.log.json
Training Log: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/20210606_205006.log
Weights: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb/tanet_r50_1x1x8_50e_sthv1_rgb_20210630-f4a48609.pth
- Config: configs/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb.py
In Collection: TANet
Metadata:
Architecture: TANet
Batch Size: 8
Epochs: 50
FLOPs: 65946542336
Parameters: 25134670
Pretrained: ImageNet
Resolution: height 100
Training Data: SthV1
gpus: 4
Modality: RGB
Name: tanet_r50_1x1x16_50e_sthv1_rgb
Results:
- Dataset: SthV1
Metrics:
Top 1 Accuracy: 50.91
Top 1 Accuracy (efficient): 49.05
Top 5 Accuracy: 79.13
Top 5 Accuracy (efficient): 77.90
Task: Action Recognition
Training Json Log: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb.json
Training Log: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb.log
Weights: https://download.openmmlab.com/mmaction/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb/tanet_r50_1x1x16_50e_sthv1_rgb_20211202-370c2128.pth
openmmlab_test/mmaction2-0.24.1/configs/recognition/tanet/tanet_r50_1x1x16_50e_sthv1_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/tanet_r50.py', '../../_base_/default_runtime.py',
'../../_base_/schedules/sgd_tsm_50e.py'
]
# model settings
model = dict(
backbone=dict(num_segments=16),
cls_head=dict(num_classes=174, num_segments=16, dropout_ratio=0.6))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/sthv1/rawframes'
data_root_val = 'data/sthv1/rawframes'
ann_file_train = 'data/sthv1/sthv1_train_list_rawframes.txt'
ann_file_val = 'data/sthv1/sthv1_val_list_rawframes.txt'
ann_file_test = 'data/sthv1/sthv1_val_list_rawframes.txt'
sthv1_flip_label_map = {2: 4, 4: 2, 30: 41, 41: 30, 52: 66, 66: 52}
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16),
dict(type='RawFrameDecode'),
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=sthv1_flip_label_map),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=16,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=16,
twice_sample=True,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=4,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
filename_tmpl='{:05}.jpg',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
filename_tmpl='{:05}.jpg',
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
filename_tmpl='{:05}.jpg',
pipeline=test_pipeline))
evaluation = dict(
interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(lr=0.005, weight_decay=0.001)
lr_config = dict(policy='step', step=[30, 40, 45])
# runtime settings
work_dir = './work_dirs/tanet_r50_1x1x16_50e_sthv1_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tanet/tanet_r50_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/tanet_r50.py', '../../_base_/default_runtime.py',
'../../_base_/schedules/sgd_tsm_50e.py'
]
# model settings
model = dict(cls_head=dict(num_classes=174, dropout_ratio=0.6))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/sthv1/rawframes'
data_root_val = 'data/sthv1/rawframes'
ann_file_train = 'data/sthv1/sthv1_train_list_rawframes.txt'
ann_file_val = 'data/sthv1/sthv1_val_list_rawframes.txt'
ann_file_test = 'data/sthv1/sthv1_val_list_rawframes.txt'
sthv1_flip_label_map = {2: 4, 4: 2, 30: 41, 41: 30, 52: 66, 66: 52}
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8),
dict(type='RawFrameDecode'),
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=sthv1_flip_label_map),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
filename_tmpl='{:05}.jpg',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
filename_tmpl='{:05}.jpg',
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
filename_tmpl='{:05}.jpg',
pipeline=test_pipeline))
evaluation = dict(
interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.001)
lr_config = dict(policy='step', step=[30, 40, 45])
# runtime settings
work_dir = './work_dirs/tanet_r50_1x1x8_50e_sthv1_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tanet/tanet_r50_dense_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 37437e80
_base_ = [
'../../_base_/models/tanet_r50.py', '../../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='DenseSampleFrames', clip_len=1, frame_interval=1, num_clips=8),
dict(type='RawFrameDecode'),
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='DenseSampleFrames',
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='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='DenseSampleFrames',
clip_len=1,
frame_interval=1,
num_clips=8,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=8,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
train=dict(
type=dataset_type,
ann_file=ann_file_train,
data_prefix=data_root,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline))
evaluation = dict(
interval=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD',
constructor='TSMOptimizerConstructor',
paramwise_cfg=dict(fc_lr5=True),
lr=0.01, # this lr is used for 8 gpus
momentum=0.9,
weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[50, 75, 90])
total_epochs = 100
# runtime settings
work_dir = './work_dirs/tanet_r50_dense_1x1x8_100e_kinetics400_rgb/'
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment