I don't know why this procsee wrong

[sinyoung-park]

Hi, I using MMpretrain. and i use Resnet34 and i modified it. anyway, I was using it well until 3 days ago, when suddenly I ran train.py and got an error. TypeError: class CustomDataset in mmpretrain/datasets/custom.py: BaseDataset.init() got an unexpected keyword argument 'split'. i don't torch any other code. and i trying to find error. but the base_dataset.py and custom.py code not have problem. how can i fix? Did something happen to your split in the meantime?

[Ezra-Yu]

class CustomDataset don't have a parameter of split. please refer to this doc.

[sinyoung-park]

i read refer, but i don't think fix my problem. please help me.
the custom.py is
def__int__( is not have split. @DATASETS.register_module()
class CustomDataset(BaseDataset):
def init(
self,
data_root: str = '',
data_prefix: Union[str, dict] = '',
with_label: bool = True,
extensions: Sequence[str] = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif'),
metainfo: Optional[dict] = None,
lazy_init: bool = False,
**kwargs
):
assert (data_prefix or data_root), 'One of data_root and data_prefix must be specified.'

    self.extensions = tuple(set([i.lower() for i in extensions]))
    self.with_label = with_label

    super().__init__(
        data_root=data_root,
        data_prefix=data_prefix,
        metainfo=metainfo,
        lazy_init=True,
        **kwargs
    )

    # Full initialize the dataset.
    if not lazy_init:
        self.full_init()

and my config file is
%%writefile configs/resnet/resnet34_8xb32_in1k_custom.py
base = [
'../base/models/resnet34.py', '../base/datasets/imagenet_bs32.py',
'../base/schedules/imagenet_bs256.py', '../base/default_runtime.py'
]

model settings

model = dict(
type='ImageClassifier',
backbone=dict(
type='ResNet',
depth=34,
num_stages=4,
out_indices=(3, ),
style='pytorch'),
neck=dict(type='GlobalAveragePooling'),
head=dict(
type='LinearClsHead',
num_classes=5,
in_channels=512,
loss=dict(type='CrossEntropyLoss', loss_weight=0.8),
topk=(1, 5),
))

dataset settings

dataset_type = 'CustomDataset',
data_preprocessor = dict(
num_classes=5,
# RGB format normalization parameters
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
# convert image from BGR to RGB
to_rgb=True,
)

train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', scale=224),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='PackInputs'),
]

test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='ResizeEdge', scale=256, edge='short'),
dict(type='CenterCrop', crop_size=224),
dict(type='PackInputs'),
]

train_dataloader = dict(
batch_size=16,
num_workers=5,
dataset=dict(
type='CustomDataset',
data_root='/content/mmpretrain/pcldata/potentialcore230522',
ann_file='/content/mmpretrain/pcldata/potentialcore230522/train.txt',
data_prefix='train_set',
with_label=True,
classes=['8slm','12slm','16slm','20slm','24slm'],
pipeline=train_pipeline),
sampler=dict(type='DefaultSampler', shuffle=True),
)

val_dataloader = dict(
batch_size=16,
num_workers=5,
dataset=dict(
type=dataset_type,
data_root='/content/mmpretrain/pcldata/potentialcore230522',
ann_file='/content/mmpretrain/pcldata/potentialcore230522/val.txt',
data_prefix='val_set',
with_label=True,
classes=['8slm','12slm','16slm','20slm','24slm'],
pipeline=test_pipeline),
sampler=dict(type='DefaultSampler', shuffle=True),
)

test_dataloader = dict(
batch_size=16,
num_workers=5,
dataset=dict(
type=dataset_type,
data_root='/content/mmpretrain/pcldata/potentialcore230522',
ann_file='/content/mmpretrain/pcldata/potentialcore230522/test.txt',
data_prefix='test_set',
with_label=True,
classes=['8slm','12slm','16slm','20slm','24slm'],
pipeline=test_pipeline),
sampler=dict(type='DefaultSampler', shuffle=False),
)
val_evaluator = dict(type='Accuracy', topk=(1, 5))

optimizer

optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.025, momentum=0.9, weight_decay=0.0001,dampening=0.001))

learning policy

param_scheduler = dict(
type='MultiStepLR', by_epoch=True, milestones=[10, 20, 30], gamma=0.1)

train, val, test setting

train_cfg = dict(by_epoch=True, max_epochs=25, val_interval=1)
val_cfg = dict()
test_cfg = dict()

NOTE: auto_scale_lr is for automatically scaling LR,

based on the actual training batch size.

auto_scale_lr = dict(base_batch_size=256)

defaults to use registries in mmpretrain

default_scope = 'mmpretrain'

configure default hooks

default_hooks = dict(
# record the time of every iteration.
timer=dict(type='IterTimerHook'),

# print log every 100 iterations.
logger=dict(type='LoggerHook', interval=100),

# enable the parameter scheduler.
param_scheduler=dict(type='ParamSchedulerHook'),

# save checkpoint per epoch.
checkpoint=dict(type='CheckpointHook', interval=1),

# set sampler seed in distributed evrionment.
sampler_seed=dict(type='DistSamplerSeedHook'),

# validation results visualization, set True to enable it.
visualization=dict(type='VisualizationHook', enable=False),

)

configure environment

env_cfg = dict(
# whether to enable cudnn benchmark
cudnn_benchmark=False,

# set multi process parameters
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),

# set distributed parameters
dist_cfg=dict(backend='nccl'),

)

set visualizer

vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(type='UniversalVisualizer', vis_backends=vis_backends)

set log level

log_level = 'INFO'

load from which checkpoint

load_from = None

whether to resume training from the loaded checkpoint

resume = False

Defaults to use random seed and disable deterministic

randomness = dict(seed=1, deterministic=True)
terministic=True)

[sinyoung-park]

i solve this problem. the error code is cause the split=' ' is not exist the custom.py class CustomDataset. init Why is this happening? i don't think so. Anyway, thanks for the answer

[Leezp99]

how can you solve this problem? I meet this question, too.

[sinyoung-park]

insert split=' ' in to dataset/custom.py like this

def init(self,
data_root: str = '',
data_prefix: Union[str, dict] = '',
ann_file: str = '',
split=' ',
with_label=True,
extensions: Sequence[str] = ('.jpg', '.jpeg', '.png', '.ppm',
'.bmp', '.pgm', '.tif'),
metainfo: Optional[dict] = None,
lazy_init: bool = False,
**kwargs):
assert (ann_file or data_prefix or data_root),
'One of ann_file, data_root and data_prefix must '
'be specified.'

    self.extensions = tuple(set([i.lower() for i in extensions]))
    self.with_label = with_label

and you can solve this problem

[Julan-zy]

insert split=' ' in to dataset/custom.py like this

def init(self, data_root: str = '', data_prefix: Union[str, dict] = '', ann_file: str = '', split=' ', with_label=True, extensions: Sequence[str] = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif'), metainfo: Optional[dict] = None, lazy_init: bool = False, **kwargs): assert (ann_file or data_prefix or data_root), 'One of ann_file, data_root and data_prefix must ' 'be specified.'

    self.extensions = tuple(set([i.lower() for i in extensions]))
    self.with_label = with_label

and you can solve this problem

Hello! I meet this question, too. I added the line "split=' '," as you did, but a new error message appears:
Traceback (most recent call last):
File "tools/train.py", line 162, in
main()
File "tools/train.py", line 158, in main
runner.train()
File "C:\Users\Julan\anaconda3\envs\openmmlab\lib\site-packages\mmengine\runner\runner.py", line 1733, in train
self.optim_wrapper = self.build_optim_wrapper(self.optim_wrapper)
File "C:\Users\Julan\anaconda3\envs\openmmlab\lib\site-packages\mmengine\runner\runner.py", line 1114, in build_optim_wrapper
return build_optim_wrapper(self.model, optim_wrapper)
File "C:\Users\Julan\anaconda3\envs\openmmlab\lib\site-packages\mmengine\optim\optimizer\builder.py", line 210, in build_optim_wrapper
optim_wrapper = optim_wrapper_constructor(model)
File "C:\Users\Julan\anaconda3\envs\openmmlab\lib\site-packages\mmengine\optim\optimizer\default_constructor.py", line 318, in call
optimizer = OPTIMIZERS.build(optimizer_cfg)
File "C:\Users\Julan\anaconda3\envs\openmmlab\lib\site-packages\mmengine\registry\registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "C:\Users\Julan\anaconda3\envs\openmmlab\lib\site-packages\mmengine\registry\build_functions.py", line 121, in build_from_cfg
obj = obj_cls(**args) # type: ignore
TypeError: init() got an unexpected keyword argument 'momentum'