[Bug] batch_size problem

Question

[Bug] batch_size problem

Sunshulong opened this issue a month ago · comments

Sunshulong commented a month ago

Branch

main branch (1.x version, such as v1.0.0, or dev-1.x branch)

Prerequisite

I have searched Issues and Discussions but cannot get the expected help.
I have read the documentation but cannot get the expected help.
The bug has not been fixed in the latest version.

Environment

base = '../../base/default_runtime.py'

model = dict(
type='Recognizer3D',
backbone=dict(
type='UniFormer',
depth=[3, 4, 8, 3],
embed_dim=[64, 128, 320, 512],
head_dim=64,
drop_path_rate=0.1),
cls_head=dict(
type='I3DHead',
dropout_ratio=0.,
num_classes=120,
in_channels=512,
average_clips='prob'),
data_preprocessor=dict(
type='ActionDataPreprocessor',
mean=[114.75, 114.75, 114.75],
std=[57.375, 57.375, 57.375],
format_shape='NCTHW'))

dataset_type = 'PoseDataset'
ann_file = 'data/skeleton/ntu120_2d.pkl'
left_kp = [1, 3, 5, 7, 9, 11, 13, 15]
right_kp = [2, 4, 6, 8, 10, 12, 14, 16]
train_pipeline = [
dict(type='UniformSampleFrames', clip_len=48),
dict(type='PoseDecode'),
dict(type='PoseCompact', hw_ratio=1., allow_imgpad=True),
dict(type='Resize', scale=(-1, 64)),
dict(type='RandomResizedCrop', area_range=(0.56, 1.0)),
dict(type='Resize', scale=(56, 56), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5, left_kp=left_kp, right_kp=right_kp),
dict(
type='GeneratePoseTarget',
sigma=0.6,
use_score=True,
with_kp=True,
with_limb=False),
dict(type='FormatShape', input_format='NCTHW_Heatmap'),
dict(type='PackActionInputs')
]
val_pipeline = [
dict(type='UniformSampleFrames', clip_len=48, num_clips=1, test_mode=True),
dict(type='PoseDecode'),
dict(type='PoseCompact', hw_ratio=1., allow_imgpad=True),
dict(type='Resize', scale=(-1, 64)),
dict(type='CenterCrop', crop_size=64),
dict(
type='GeneratePoseTarget',
sigma=0.6,
use_score=True,
with_kp=True,
with_limb=False),
dict(type='FormatShape', input_format='NCTHW_Heatmap'),
dict(type='PackActionInputs')
]
test_pipeline = [
dict(
type='UniformSampleFrames', clip_len=48, num_clips=10, test_mode=True),
dict(type='PoseDecode'),
dict(type='PoseCompact', hw_ratio=1., allow_imgpad=True),
dict(type='Resize', scale=(-1, 64)),
dict(type='CenterCrop', crop_size=64),
dict(
type='GeneratePoseTarget',
sigma=0.6,
use_score=True,
with_kp=True,
with_limb=False,
double=True,
left_kp=left_kp,
right_kp=right_kp),
dict(type='FormatShape', input_format='NCTHW_Heatmap'),
dict(type='PackActionInputs')
]

train_dataloader = dict(
batch_size=3,
num_workers=16,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type='RepeatDataset',
times=1,
dataset=dict(
type=dataset_type,
ann_file=ann_file,
split='xsub_train',
pipeline=train_pipeline)))
val_dataloader = dict(
batch_size=3,
num_workers=16,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
ann_file=ann_file,
split='xsub_val',
pipeline=val_pipeline,
test_mode=True))
test_dataloader = dict(
batch_size=3,
num_workers=16,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
ann_file=ann_file,
split='xsub_val',
pipeline=test_pipeline,
test_mode=True))

val_evaluator = [dict(type='AccMetric')]
test_evaluator = val_evaluator

train_cfg = dict(
type='EpochBasedTrainLoop', max_epochs=24, val_begin=1, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')

param_scheduler = [
dict(
type='CosineAnnealingLR',
eta_min=0,
T_max=24,
by_epoch=True,
convert_to_iter_based=True)
]

optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0003),
clip_grad=dict(max_norm=40, norm_type=2))

Describe the bug

Hello, first of all I would like to ask, will batch_size change during the training process?
I replaced posec3d's feature extraction network with uniformer, and the above is my configuration file. But something went wrong in data_preprocessor.py. Even in the first round of training, the batch_size was still displayed as 3 normally, but later the batch_size became 2. Below is part of my training log. Please help to answer this question.

Reproduces the problem - code sample

No response

Reproduces the problem - command or script

No response

Reproduces the problem - error message

No response

Additional information

No response