SLCA

Arguments

Options

--prefixstr

Help: None

• Default: reproduce

--memory_sizeint

Help: None

• Default: 0

--memory_per_classint

Help: None

• Default: 0

--fixed_memory0|1|True|False -> bool

Help: None

• Default: 0

--feature_extractor_typestr

Help: the type of feature extractor to use. vit-b-p16 is the default: ViT-B/16 pretrained on Imagenet 21k (NO finetuning on ImageNet 1k)

• Default: vit-b-p16

--ca_epochsint

Help: number of epochs for classifier alignment

• Default: 5

--ca_with_logit_normfloat

Help: None

• Default: 0.1

--milestonesstr

Help: None

• Default: 40

--lr_decayfloat

Help: None

• Default: 0.1

--virtual_bs_iterationsint

Help: virtual batch size iterations

• Default: 1

Slow Learner with Classifier Alignment.

Note

SLCA USES A CUSTOM BACKBONE (see feature_extractor_type argument)

param –feature_extractor_type:

the type of convnet to use. vit-b-p16 is the default: ViT-B/16 pretrained on Imagenet 21k (NO finetuning on ImageNet 1k)

Classes

class models.slca.SLCA(backbone, loss, args, transform, dataset=None)

Bases: ContinualModel

Continual Learning via Slow Learner with Classifier Alignment.

COMPATIBILITY: List[str] = ['class-il', 'domain-il', 'task-il']

NAME: str = 'slca'

begin_task(dataset)

end_task(dataset)

forward(x)

get_parameters()

static get_parser(parser)

Return type:

ArgumentParser

observe(inputs, labels, not_aug_inputs, epoch=0)