Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add TimesFormer configuration files #1658

Open
wants to merge 13 commits into
base: 0.x
Choose a base branch
from
Original file line number Diff line number Diff line change
@@ -0,0 +1,125 @@
"""MMaction2中的timesformer使用视频帧作为数据集,这里改成用视频做数据集的."""
_base_ = ['../../_base_/default_runtime.py']

# model settings
model = dict(
type='Recognizer3D',
backbone=dict(
type='TimeSformer',
pretrained= # noqa: E251
'https://download.openmmlab.com/mmaction/recognition/timesformer/vit_base_patch16_224.pth', # noqa: E501
num_frames=8,
img_size=224,
patch_size=16,
embed_dims=768,
in_channels=3,
dropout_ratio=0.,
transformer_layers=None,
attention_type='divided_space_time',
norm_cfg=dict(type='LN', eps=1e-6)),
cls_head=dict(type='TimeSformerHead', num_classes=400, in_channels=768),
# model training and testing settings
train_cfg=None,
test_cfg=dict(average_clips='prob'))

# 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=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_bgr=False)

train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=8, frame_interval=32, 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=8,
frame_interval=32,
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=8,
frame_interval=32,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='ThreeCrop', 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'])
]
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(
type='SGD',
lr=0.005,
momentum=0.9,
paramwise_cfg=dict(
custom_keys={
'.backbone.cls_token': dict(decay_mult=0.0),
'.backbone.pos_embed': dict(decay_mult=0.0),
'.backbone.time_embed': dict(decay_mult=0.0)
}),
weight_decay=1e-4,
nesterov=True) # 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='step', step=[5, 10])
total_epochs = 15

# runtime settings
checkpoint_config = dict(interval=1)
work_dir = './work_dirs/timesformer_divST_8x32x1_15e_kinetics400_rgb'
Original file line number Diff line number Diff line change
@@ -0,0 +1,123 @@
_base_ = ['../../_base_/default_runtime.py']

# model settings
model = dict(
type='Recognizer3D',
backbone=dict(
type='TimeSformer',
pretrained= # noqa: E251
'https://download.openmmlab.com/mmaction/recognition/timesformer/vit_base_patch16_224.pth', # noqa: E501
num_frames=8,
img_size=224,
patch_size=16,
embed_dims=768,
in_channels=3,
dropout_ratio=0.,
transformer_layers=None,
attention_type='joint_space_time',
norm_cfg=dict(type='LN', eps=1e-6)),
cls_head=dict(type='TimeSformerHead', num_classes=400, in_channels=768),
# model training and testing settings
train_cfg=None,
test_cfg=dict(average_clips='prob'))

# 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=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_bgr=False)

train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=8, frame_interval=32, 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=8,
frame_interval=32,
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=8,
frame_interval=32,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='ThreeCrop', 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'])
]
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(
type='SGD',
lr=0.004375,
momentum=0.9,
paramwise_cfg=dict(
custom_keys={
'.backbone.cls_token': dict(decay_mult=0.0),
'.backbone.pos_embed': dict(decay_mult=0.0),
'.backbone.time_embed': dict(decay_mult=0.0)
}),
weight_decay=1e-4,
nesterov=True) # 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='step', step=[5, 10])
total_epochs = 15

# runtime settings
checkpoint_config = dict(interval=1)
work_dir = './work_dirs/timesformer_divST_8x32x1_15e_kinetics400_rgb'
Original file line number Diff line number Diff line change
@@ -0,0 +1,125 @@
_base_ = ['../../_base_/default_runtime.py']
'''
MMaction2中的timesformer使用视频帧作为数据集,这里改成用视频做数据集的
这个显存占用相比 Div 小
'''
# model settings
model = dict(
type='Recognizer3D',
backbone=dict(
type='TimeSformer',
pretrained= # noqa: E251
'https://download.openmmlab.com/mmaction/recognition/timesformer/vit_base_patch16_224.pth', # noqa: E501
num_frames=8,
img_size=224,
patch_size=16,
embed_dims=768,
in_channels=3,
dropout_ratio=0.,
transformer_layers=None,
attention_type='space_only',
norm_cfg=dict(type='LN', eps=1e-6)),
cls_head=dict(type='TimeSformerHead', num_classes=400, in_channels=768),
# model training and testing settings
train_cfg=None,
test_cfg=dict(average_clips='prob'))

# 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=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_bgr=False)

train_pipeline = [
dict(type='DecordInit'),
dict(type='SampleFrames', clip_len=8, frame_interval=32, 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=8,
frame_interval=32,
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=8,
frame_interval=32,
num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='ThreeCrop', 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'])
]
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(
type='SGD',
lr=0.005,
momentum=0.9,
paramwise_cfg=dict(
custom_keys={
'.backbone.cls_token': dict(decay_mult=0.0),
'.backbone.pos_embed': dict(decay_mult=0.0)
}),
weight_decay=1e-4,
nesterov=True) # 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='step', step=[5, 10])
total_epochs = 15

# runtime settings
checkpoint_config = dict(interval=1)
work_dir = './work_dirs/timesformer_divST_8x32x1_15e_kinetics400_rgb'