Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "1fd7e118901a91eeaf1c723755c86349ffad41c8"
Commit 76ccaa54 authored by unknown's avatar unknown
Browse files

添加mmaction2测试用例

parent 44c28b2b
Hide whitespace changes
Inline Side-by-side
Showing with 1735 additions and 0 deletions
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train_320p'
data_root_val = 'data/kinetics400/rawframes_val_320p'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes_320p.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes_320p.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes_320p.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=1, frame_interval=1, num_clips=8),
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='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=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'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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=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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.00375, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
# runtime settings
work_dir = './work_dirs/tsn_r50_320p_1x1x8_100e_kinetics400_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow.py 0 → 100644
View file @ 76ccaa54
_base_ = ['../../_base_/models/tsn_r50.py', '../../_base_/default_runtime.py']
# model settings
# ``in_channels`` should be 2 * clip_len
model = dict(backbone=dict(in_channels=10))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train_320p'
data_root_val = 'data/kinetics400/rawframes_val_320p'
ann_file_train = 'data/kinetics400/kinetics400_flow_train_list_320p.txt'
ann_file_val = 'data/kinetics400/kinetics400_flow_val_list_320p.txt'
ann_file_test = 'data/kinetics400/kinetics400_flow_val_list_320p.txt'
img_norm_cfg = dict(mean=[128, 128], std=[128, 128])
train_pipeline = [
dict(type='SampleFrames', clip_len=5, frame_interval=1, num_clips=8),
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='NCHW_Flow'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=5,
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_Flow'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=5,
frame_interval=1,
num_clips=25,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW_Flow'),
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,
filename_tmpl='{}_{:05d}.jpg',
modality='Flow',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
filename_tmpl='{}_{:05d}.jpg',
modality='Flow',
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
filename_tmpl='{}_{:05d}.jpg',
modality='Flow',
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
type='SGD', lr=0.001875, 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='step', step=[70, 100])
total_epochs = 110
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r50_320p_1x1x8_110e_kinetics400_flow/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_320p_1x1x8_150e_activitynet_clip_flow.py 0 → 100644
View file @ 76ccaa54
_base_ = ['../../_base_/models/tsn_r50.py', '../../_base_/default_runtime.py']
# model settings
# ``in_channels`` should be 2 * clip_len
model = dict(
backbone=dict(in_channels=10),
cls_head=dict(num_classes=200, dropout_ratio=0.8))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/ActivityNet/rawframes'
data_root_val = 'data/ActivityNet/rawframes'
ann_file_train = 'data/ActivityNet/anet_train_clip.txt'
ann_file_val = 'data/ActivityNet/anet_val_clip.txt'
ann_file_test = 'data/ActivityNet/anet_val_clip.txt'
img_norm_cfg = dict(mean=[128, 128], std=[128, 128], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=5, frame_interval=1, num_clips=8),
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='NCHW_Flow'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=5,
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_Flow'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=5,
frame_interval=1,
num_clips=25,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW_Flow'),
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='flow_{}_{:05d}.jpg',
with_offset=True,
modality='Flow',
start_index=0,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
filename_tmpl='flow_{}_{:05d}.jpg',
with_offset=True,
modality='Flow',
start_index=0,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
filename_tmpl='flow_{}_{:05d}.jpg',
with_offset=True,
modality='Flow',
start_index=0,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(type='SGD', lr=0.001, 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='step', step=[60, 120])
total_epochs = 150
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r50_320p_1x1x8_150e_activitynet_clip_flow/'
load_from = ('https://download.openmmlab.com/mmaction/recognition/tsn/'
'tsn_r50_320p_1x1x8_110e_kinetics400_flow/'
'tsn_r50_320p_1x1x8_110e_kinetics400_flow_20200705-1f39486b.pth')
workflow = [('train', 5)]
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_320p_1x1x8_150e_activitynet_video_flow.py 0 → 100644
View file @ 76ccaa54
_base_ = ['../../_base_/models/tsn_r50.py', '../../_base_/default_runtime.py']
# model settings
# ``in_channels`` should be 2 * clip_len
model = dict(
backbone=dict(in_channels=10),
cls_head=dict(num_classes=200, dropout_ratio=0.8))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/ActivityNet/rawframes'
data_root_val = 'data/ActivityNet/rawframes'
ann_file_train = 'data/ActivityNet/anet_train_video.txt'
ann_file_val = 'data/ActivityNet/anet_val_video.txt'
ann_file_test = 'data/ActivityNet/anet_val_clip.txt'
img_norm_cfg = dict(mean=[128, 128], std=[128, 128], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=5, frame_interval=1, num_clips=8),
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='NCHW_Flow'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(
type='SampleFrames',
clip_len=5,
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_Flow'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=5,
frame_interval=1,
num_clips=25,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW_Flow'),
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='flow_{}_{:05d}.jpg',
modality='Flow',
start_index=0,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
filename_tmpl='flow_{}_{:05d}.jpg',
modality='Flow',
start_index=0,
pipeline=val_pipeline),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
filename_tmpl='flow_{}_{:05d}.jpg',
with_offset=True,
modality='Flow',
start_index=0,
pipeline=test_pipeline))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(type='SGD', lr=0.001, 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='step', step=[60, 120])
total_epochs = 150
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r50_320p_1x1x8_150e_activitynet_video_flow/'
load_from = ('https://download.openmmlab.com/mmaction/recognition/tsn/'
'tsn_r50_320p_1x1x8_110e_kinetics400_flow/'
'tsn_r50_320p_1x1x8_110e_kinetics400_flow_20200705-1f39486b.pth')
workflow = [('train', 5)]
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_320p_1x1x8_50e_activitynet_clip_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=200, dropout_ratio=0.8))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/ActivityNet/rawframes'
data_root_val = 'data/ActivityNet/rawframes'
ann_file_train = 'data/ActivityNet/anet_train_clip.txt'
ann_file_val = 'data/ActivityNet/anet_val_clip.txt'
ann_file_test = 'data/ActivityNet/anet_val_clip.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=1, frame_interval=1, num_clips=8),
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='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=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'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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,
with_offset=True,
start_index=0,
filename_tmpl='image_{:05d}.jpg'),
val=dict(
type=dataset_type,
ann_file=ann_file_val,
data_prefix=data_root_val,
pipeline=val_pipeline,
with_offset=True,
start_index=0,
filename_tmpl='image_{:05d}.jpg'),
test=dict(
type=dataset_type,
ann_file=ann_file_test,
data_prefix=data_root_val,
pipeline=test_pipeline,
with_offset=True,
start_index=0,
filename_tmpl='image_{:05d}.jpg'))
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
# runtime settings
work_dir = './work_dirs/tsn_r50_320p_1x1x8_50e_activitynet_clip_rgb/'
load_from = ('https://download.openmmlab.com/mmaction/recognition/tsn/'
'tsn_r50_320p_1x1x8_100e_kinetics400_rgb/'
'tsn_r50_320p_1x1x8_100e_kinetics400_rgb_20200702-ef80e3d7.pth')
workflow = [('train', 5)]
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_320p_1x1x8_50e_activitynet_video_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=200, dropout_ratio=0.8))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/ActivityNet/rawframes'
data_root_val = 'data/ActivityNet/rawframes'
ann_file_train = 'data/ActivityNet/anet_train_video.txt'
ann_file_val = 'data/ActivityNet/anet_val_video.txt'
ann_file_test = 'data/ActivityNet/anet_val_video.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=1, frame_interval=1, num_clips=8),
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='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=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'])
]
test_pipeline = [
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
# runtime settings
work_dir = './work_dirs/tsn_r50_320p_1x1x8_50e_activitynet_video_rgb/'
load_from = ('https://download.openmmlab.com/mmaction/recognition/tsn/'
'tsn_r50_320p_1x1x8_100e_kinetics400_rgb/'
'tsn_r50_320p_1x1x8_100e_kinetics400_rgb_20200702-ef80e3d7.pth')
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_clip_feature_extraction_1x1x3_rgb.py 0 → 100644
View file @ 76ccaa54
# model settings
model = dict(
type='Recognizer2D',
backbone=dict(
type='ResNet',
pretrained='torchvision://resnet50',
depth=50,
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', num_threads=1),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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='NCHW'),
dict(type='Collect', keys=['imgs'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=1,
workers_per_gpu=2,
test_dataloader=dict(videos_per_gpu=1),
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/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(dropout_ratio=0.5, init_std=0.001))
# 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=5),
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='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'])
]
data = dict(
videos_per_gpu=16,
workers_per_gpu=2,
val_dataloader=dict(videos_per_gpu=1),
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', lr=0.03, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
# runtime settings
work_dir = './work_dirs/tsn_r50_dense_1x1x5_100e_kinetics400_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.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='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'])
]
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=0.005, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
# runtime settings
work_dir = './work_dirs/tsn_r50_dense_1x1x8_100e_kinetics400_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_inference_1x1x3_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = ['../../_base_/models/tsn_r50.py']
# dataset settings
dataset_type = 'RawframeDataset'
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='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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'], 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/tsn/tsn_r50_video_1x1x16_100e_diving48_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=48))
# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/diving48/videos'
data_root_val = 'data/diving48/videos'
ann_file_train = 'data/diving48/diving48_train_list_videos.txt'
ann_file_val = 'data/diving48/diving48_val_list_videos.txt'
ann_file_test = 'data/diving48/diving48_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=1, frame_interval=1, num_clips=16),
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),
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='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=16,
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=16,
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='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,
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 = dict(
type='SGD',
lr=0.00125, # this lr is used for 8 gpus
momentum=0.9,
weight_decay=0.0001)
# runtime settings
work_dir = './work_dirs/tsn_r50_video_1x1x16_100e_diving48_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_1x1x8_100e_diving48_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=48))
# dataset settings
dataset_type = 'VideoDataset'
data_root = 'data/diving48/videos'
data_root_val = 'data/diving48/videos'
ann_file_train = 'data/diving48/diving48_train_list_videos.txt'
ann_file_val = 'data/diving48/diving48_val_list_videos.txt'
ann_file_test = 'data/diving48/diving48_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=1, frame_interval=1, num_clips=8),
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),
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='DecordInit'),
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='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='DecordInit'),
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='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=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
optimizer = dict(
type='SGD',
lr=0.0025, # this lr is used for 8 gpus
momentum=0.9,
weight_decay=0.0001)
# runtime settings
work_dir = './work_dirs/tsn_r50_video_1x1x8_100e_diving48_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# 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=1, frame_interval=1, num_clips=8),
dict(type='DecordDecode'),
dict(
type='MultiScaleCrop',
input_size=224,
scales=(1, 0.875, 0.75, 0.66),
random_crop=False,
max_wh_scale_gap=1),
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='DecordInit'),
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='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='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', 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'])
]
data = dict(
videos_per_gpu=32,
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/tsn_r50_video_1x1x8_100e_kinetics400_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics600_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(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=1, frame_interval=1, num_clips=8),
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
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=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'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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='NCHW'),
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=0.00375, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r50_1x1x3_100e_kinetics600_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics700_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=700))
# dataset settings
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=1, frame_interval=1, num_clips=8),
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
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=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'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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='NCHW'),
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=0.00375, momentum=0.9,
weight_decay=0.0001) # this lr is used for 8 gpus
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsn_r50_1x1x3_100e_kinetics700_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_320p_1x1x3_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# 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=1, frame_interval=1, num_clips=3),
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs', 'label'])
]
val_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=3,
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
test_pipeline = [
dict(type='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=32,
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/tsn_r50_video_1x1x3_100e_kinetics400_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/models/tsn_r50.py', '../../_base_/schedules/sgd_100e.py',
'../../_base_/default_runtime.py'
]
# 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='DenseSampleFrames', clip_len=1, frame_interval=1, num_clips=8),
dict(type='DecordDecode'),
dict(
type='MultiScaleCrop',
input_size=224,
scales=(1, 0.875, 0.75, 0.66),
random_crop=False,
max_wh_scale_gap=1),
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='DecordInit'),
dict(
type='DenseSampleFrames',
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='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='DecordInit'),
dict(
type='DenseSampleFrames',
clip_len=1,
frame_interval=1,
num_clips=8,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', 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'])
]
data = dict(
videos_per_gpu=32,
workers_per_gpu=2,
val_dataloader=dict(videos_per_gpu=1),
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/tsn_r50_video_dense_1x1x8_100e_kinetics400_rgb/'
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_imgaug_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
# model settings
model = dict(
type='Recognizer2D',
backbone=dict(
type='ResNet',
pretrained='torchvision://resnet50',
depth=50,
norm_eval=False),
cls_head=dict(
type='TSNHead',
num_classes=400,
in_channels=2048,
spatial_type='avg',
consensus=dict(type='AvgConsensus', dim=1),
dropout_ratio=0.4,
init_std=0.01),
train_cfg=None,
test_cfg=dict(average_clips=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=1, frame_interval=1, num_clips=8),
dict(type='DecordDecode'),
dict(
type='MultiScaleCrop',
input_size=224,
scales=(1, 0.875, 0.75, 0.66),
random_crop=False,
max_wh_scale_gap=1),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='Imgaug', transforms='default'),
# dict(
# type='Imgaug',
# transforms=[
# dict(type='Rotate', rotate=(-20, 20)),
# dict(type='Dropout', p=(0, 0.05))
# ]),
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='DecordInit'),
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='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='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=32,
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))
# optimizer
optimizer = dict(
type='SGD', lr=0.01, 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='step', step=[40, 80])
total_epochs = 100
checkpoint_config = dict(interval=1)
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])
log_config = dict(
interval=20,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook'),
])
# runtime settings
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/tsn_r50_video_1x1x8_100e_kinetics400_rgb/'
load_from = None
resume_from = None
workflow = [('train', 1)]
openmmlab_test/mmaction2-0.24.1/configs/recognition/tsn/tsn_r50_video_inference_1x1x3_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = ['../../_base_/models/tsn_r50.py']
# 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='OpenCVInit', num_threads=1),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
test_mode=True),
dict(type='OpenCVDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='FormatShape', input_format='NCHW'),
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/tsn/tsn_r50_video_mixup_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 76ccaa54
_base_ = [
'../../_base_/schedules/sgd_100e.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(
type='Recognizer2D',
backbone=dict(
type='ResNet',
pretrained='torchvision://resnet50',
depth=50,
norm_eval=False),
cls_head=dict(
type='TSNHead',
num_classes=400,
in_channels=2048,
spatial_type='avg',
consensus=dict(type='AvgConsensus', dim=1),
dropout_ratio=0.4,
init_std=0.01),
# model training and testing settings
train_cfg=dict(
blending=dict(type='MixupBlending', num_classes=400, alpha=.2)),
test_cfg=dict(average_clips=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=1, frame_interval=1, num_clips=8),
dict(type='DecordDecode'),
dict(
type='MultiScaleCrop',
input_size=224,
scales=(1, 0.875, 0.75, 0.66),
random_crop=False,
max_wh_scale_gap=1),
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='DecordInit'),
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='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='DecordInit'),
dict(
type='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=25,
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='NCHW'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=32,
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/tsn_r50_video_mixup_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