AGEM R#

Arguments#

Rehearsal arguments

Arguments shared by all rehearsal-based methods.

--buffer_sizeint

Help: The size of the memory buffer.

  • Default: None

--minibatch_sizeint

Help: The batch size of the memory buffer.

  • Default: None

A version of A-GEM, leveraging a memory buffer with reservoir sampling.

Classes#

class models.agem_r.AGemr(backbone, loss, args, transform, dataset=None)[source]#

Bases: ContinualModel

Continual learning via A-GEM, leveraging a reservoir buffer.

COMPATIBILITY: List[str] = ['class-il', 'domain-il', 'task-il', 'general-continual']#
NAME: str = 'agem_r'#
static get_parser(parser)[source]#
Return type:

ArgumentParser

observe(inputs, labels, not_aug_inputs, epoch=None)[source]#