MER#

Arguments#

Options

--betafloat

Help: Within-batch update beta parameter.

  • Default: None

--gammafloat

Help: Across-batch update gamma parameter.

  • Default: None

--batch_numint

Help: Number of batches extracted from the buffer.

  • Default: 1

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

Classes#

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

Bases: ContinualModel

Continual Learning via Meta-Experience Replay (Alg 6).

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

ArgumentParser

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