Skip to content

GitLab

"megatron/inference/text_generation/generation.py" did not exist on "f00d0a3fc1fb59b05669ca35ddecb6d422403bfd"
Commit 5b3e36dc authored by Sugon_ldc's avatar Sugon_ldc
Browse files

add model TSM

parents
Pipeline #315 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 1574 additions and 0 deletions
configs/recognition/tsm/tsm_nl_gaussian_r50_1x1x8_50e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.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=False,
norm_cfg=dict(type='BN3d', requires_grad=True),
mode='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=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='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,
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=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/tsm_nl_gaussian_r50_1x1x8_50e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = ['./tsm_r50_1x1x8_50e_sthv1_rgb.py']
# model settings
model = dict(backbone=dict(pretrained='torchvision://resnet101', depth=101))
# runtime settings
work_dir = './work_dirs/tsm_r101_1x1x8_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = ['./tsm_r50_1x1x8_50e_sthv2_rgb.py']
# model settings
model = dict(backbone=dict(pretrained='torchvision://resnet101', depth=101))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/sthv2/rawframes'
data_root_val = 'data/sthv2/rawframes'
ann_file_train = 'data/sthv2/sthv2_train_list_rawframes.txt'
ann_file_val = 'data/sthv2/sthv2_val_list_rawframes.txt'
ann_file_test = 'data/sthv2/sthv2_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=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='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,
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(
lr=0.01, # this lr is used for 8 gpus
)
# runtime settings
work_dir = './work_dirs/tsm_r101_1x1x8_50e_sthv2_rgb/'
configs/recognition/tsm/tsm_r50_1x1x16_100e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = ['tsm_r50_1x1x16_50e_kinetics400_rgb.py']
optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[40, 80])
total_epochs = 100
work_dir = './work_dirs/tsm_r50_1x1x16_100e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(backbone=dict(num_segments=16), cls_head=dict(num_segments=16))
# 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=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),
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,
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'),
dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]),
dict(type='ToTensor', keys=['imgs'])
]
data = dict(
videos_per_gpu=6,
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(
lr=0.0075, # this lr is used for 8 gpus
)
# runtime settings
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsm_r50_1x1x16_50e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(
backbone=dict(num_segments=16),
cls_head=dict(num_classes=174, num_segments=16))
# 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'
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='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=6,
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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(
lr=0.0075, # this lr is used for 8 gpus
weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_1x1x16_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(
backbone=dict(num_segments=16),
cls_head=dict(num_classes=174, num_segments=16))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/sthv2/rawframes'
data_root_val = 'data/sthv2/rawframes'
ann_file_train = 'data/sthv2/sthv2_train_list_rawframes.txt'
ann_file_val = 'data/sthv2/sthv2_val_list_rawframes.txt'
ann_file_test = 'data/sthv2/sthv2_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=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='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=6,
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(
lr=0.0075, # this lr is used for 8 gpus
weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_1x1x16_50e_sthv2_rgb/'
configs/recognition/tsm/tsm_r50_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = ['./tsm_r50_1x1x8_50e_kinetics400_rgb.py']
optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
lr_config = dict(policy='step', step=[40, 80])
total_epochs = 100
work_dir = './work_dirs/tsm_r50_1x1x8_100e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_1x1x8_50e_jester_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=27))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/jester/rawframes'
data_root_val = 'data/jester/rawframes'
ann_file_train = 'data/jester/jester_train_list_rawframes.txt'
ann_file_val = 'data/jester/jester_val_list_rawframes.txt'
ann_file_test = 'data/jester/jester_val_list_rawframes.txt'
jester_flip_label_map = {0: 1, 1: 0, 6: 7, 7: 6}
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='RandomResizedCrop'),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5, flip_label_map=jester_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=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=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,
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,
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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_1x1x8_50e_jester_rgb/'
configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.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='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),
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,
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=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
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsm_r50_1x1x8_100e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=174))
# 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'
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='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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_1x1x8_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv2_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=174))
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/sthv2/rawframes'
data_root_val = 'data/sthv2/rawframes'
ann_file_train = 'data/sthv2/sthv2_train_list_rawframes.txt'
ann_file_val = 'data/sthv2/sthv2_val_list_rawframes.txt'
ann_file_test = 'data/sthv2/sthv2_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=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='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=6,
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(
lr=0.0075, # this lr is used for 8 gpus
weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_1x1x8_50e_sthv2_rgb/'
configs/recognition/tsm/tsm_r50_cutmix_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py'
]
# model settings
# model settings# model settings
model = dict(
type='Recognizer2D',
backbone=dict(
type='ResNetTSM',
pretrained='torchvision://resnet50',
depth=50,
norm_eval=False,
shift_div=8),
cls_head=dict(
type='TSMHead',
num_classes=174,
in_channels=2048,
spatial_type='avg',
consensus=dict(type='AvgConsensus', dim=1),
dropout_ratio=0.5,
init_std=0.001,
is_shift=True),
# model training and testing settings
train_cfg=dict(
blending=dict(type='CutmixBlending', num_classes=174, alpha=.2)),
test_cfg=dict(average_clips='prob'))
# 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'
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='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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_cutmix_1x1x8_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_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='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=8,
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'])
# runtime settings
work_dir = './work_dirs/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_dense_1x1x8_50e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = ['tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py']
optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[20, 40])
total_epochs = 50
work_dir = './work_dirs/tsm_r50_dense_1x1x8_50e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_flip_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=174))
# 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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_flip_1x1x8_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r50_flip_randaugment_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=174))
# 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='Imgaug', transforms='default'),
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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_flip_randaugment_1x1x8_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r50_gpu_normalize_1x1x8_50e_kinetics400_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
module_hooks = [
dict(
type='GPUNormalize',
hooked_module='backbone',
hook_pos='forward_pre',
input_format='NCHW',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375])
]
# 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'
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),
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='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,
test_mode=True),
dict(type='RawFrameDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='FormatShape', input_format='NCHW'),
dict(type='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
checkpoint_config = dict(interval=5)
work_dir = './work_dirs/tsm_r50_gpu_normalize_1x1x8_100e_kinetics400_rgb/'
configs/recognition/tsm/tsm_r50_mixup_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py'
]
# model settings
model = dict(
type='Recognizer2D',
backbone=dict(
type='ResNetTSM',
pretrained='torchvision://resnet50',
depth=50,
norm_eval=False,
shift_div=8),
cls_head=dict(
type='TSMHead',
num_classes=174,
in_channels=2048,
spatial_type='avg',
consensus=dict(type='AvgConsensus', dim=1),
dropout_ratio=0.5,
init_std=0.001,
is_shift=True),
# model training and testing settings
train_cfg=dict(
blending=dict(type='MixupBlending', num_classes=174, alpha=.2)),
test_cfg=dict(average_clips='prob'))
# 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'
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='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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_mixup_1x1x8_50e_sthv1_rgb/'
configs/recognition/tsm/tsm_r50_ptv_augmix_1x1x8_50e_sthv1_rgb.py 0 → 100644
View file @ 5b3e36dc
_base_ = [
'../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
'../../_base_/default_runtime.py'
]
# model settings
model = dict(cls_head=dict(num_classes=174))
# 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'
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='pytorchvideo.AugMix'),
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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
# optimizer
optimizer = dict(weight_decay=0.0005)
# runtime settings
work_dir = './work_dirs/tsm_r50_ptv_augmix_1x1x8_50e_sthv1_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