Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

add data benchmark for tsn #57

Merged
merged 7 commits into from
Aug 4, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions configs/recognition/tsn/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,21 @@

Here, We use [1: 1] to indicate that we combine rgb and flow score with coefficients 1: 1 to get the two-stream prediction (without applying softmax).

### Kinetics-400 Data Benchmark (8-gpus, ResNet50, ImageNet pretrain; 3 segments)

In data benchmark, we compare: 1. Different data preprocessing methods: (1) Resize video to 340x256, (2) Resize the short edge of video to 320px; 2. Different data augmentation methods: (1) MultiScaleCrop, (2) RandomResizedCrop; 3. Different testing protocols: (1) 25 frames x 10 crops, (2) 25 frames x 3 crops.

| config | resolution | training augmentation | testing protocol | top1 acc | top5 acc | ckpt | log | json |
| :----------------------------------------------------------: | :------------: | :-------------------: | :--------------: | :------: | :------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| [tsn_r50_multiscalecrop_340x256_1x1x3_100e_kinetics400_rgb](data_benchmark/tsn_r50_multiscalecrop_340x256_1x1x3_100e_kinetics400_rgb.py) | 340x256 | MultiScaleCrop | 25x10 frames | 70.60 | 89.26 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/tsn_r50_1x1x3_100e_kinetics400_rgb_20200614-e508be42.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/20200614_063526.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb/20200614_063526.log.json) |
| x | 340x256 | MultiScaleCrop | 25x3 frames | 70.52 | 89.39 | x | x | x |
| [tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb](data_benchmark/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb.py) | 340x256 | RandomResizedCrop | 25x10 frames | 70.11 | 89.01 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb_20200725-88cb325a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb_20200725.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/data_benchmark/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb/tsn_r50_randomresizedcrop_340x256_1x1x3_100e_kinetics400_rgb_20200725.json) |
| x | 340x256 | RandomResizedCrop | 25x3 frames | 69.95 | 89.02 | x | x | x |
| [tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb](data_benchmark/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb.py) | short-side 320 | MultiScaleCrop | 25x10 frames | 70.32 | 89.25 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/data_benchmark/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb_20200725-9922802f.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/data_benchmark/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb_20200725.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/data_benchmark/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_multiscalecrop_320p_1x1x3_100e_kinetics400_rgb_20200725.json) |
| x | short-side 320 | MultiScaleCrop | 25x3 frames | 70.54 | 89.39 | x | x | x |
| [tsn_r50_randomresizedcrop_320p_1x1x3_100e_kinetics400_rgb](data_benchmark/tsn_r50_randomresizedcrop_320p_1x1x3_100e_kinetics400_rgb.py) | short-side 320 | RandomResizedCrop | 25x10 frames | 70.44 | 89.23 | [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_320p_1x1x3_100e_kinetics400_rgb_20200702-cc665e2a.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb/tsn_r50_f3_kinetics400_shortedge_70.9_89.5.log.json) |
| x | short-side 320 | RandomResizedCrop | 25x3 frames | 70.91 | 89.51 | x | x | x |

### Something-Something V1

|config|resolution | gpus| backbone |pretrain| top1 acc| top5 acc | reference top1 acc | reference top5 acc | gpu_mem(M) | ckpt | log| json|
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,116 @@
# 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 = None
test_cfg = dict(average_clips=None)
# 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=3),
dict(type='FrameSelector'),
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='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=3,
test_mode=True),
dict(type='FrameSelector'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Flip', flip_ratio=0),
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='FrameSelector'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', crop_size=224),
dict(type='Flip', flip_ratio=0),
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=4,
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)
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=5)
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5))
log_config = dict(
interval=20, hooks=[
dict(type='TextLoggerHook'),
])
# runtime settings
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = ('./work_dirs/tsn_r50_multiscalecrop_320p_1x1x3'
'_100e_kinetics400_rgb/')
load_from = None
resume_from = None
workflow = [('train', 5)]
Original file line number Diff line number Diff line change
@@ -0,0 +1,120 @@
# 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 = None
test_cfg = dict(average_clips=None)
# dataset settings
dataset_type = 'RawframeDataset'
data_root = 'data/kinetics400/rawframes_train'
data_root_val = 'data/kinetics400/rawframes_val'
ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False)
train_pipeline = [
dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=3),
dict(type='FrameSelector'),
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='SampleFrames',
clip_len=1,
frame_interval=1,
num_clips=3,
test_mode=True),
dict(type='FrameSelector'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=224),
dict(type='Flip', flip_ratio=0),
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='FrameSelector'),
dict(type='Resize', scale=(-1, 256)),
dict(type='TenCrop', crop_size=224),
dict(type='Flip', flip_ratio=0),
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=4,
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=5)
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5))
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_multiscalecrop_340x256_1x1x3'
'_100e_kinetics400_rgb/')
load_from = None
resume_from = None
workflow = [('train', 1)]
Original file line number Diff line number Diff line change
@@ -0,0 +1,115 @@
# 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 = None
test_cfg = dict(average_clips=None)
# 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=3),
dict(type='FrameSelector'),
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=3,
test_mode=True),
dict(type='FrameSelector'),
dict(type='Resize', scale=(-1, 256)),
dict(type='CenterCrop', crop_size=256),
dict(type='Flip', flip_ratio=0),
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='FrameSelector'),
dict(type='Resize', scale=(-1, 256)),
dict(type='ThreeCrop', crop_size=256),
dict(type='Flip', flip_ratio=0),
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=4,
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=5)
evaluation = dict(
interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5))
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_randomresizedcrop_320p_1x1x3'
'_100e_kinetics400_rgb/')
load_from = None
resume_from = None
workflow = [('train', 1)]
Loading