DER#

Arguments#

Options

--alphafloat

Help: Penalty weight.

  • Default: None

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.der.Der(backbone, loss, args, transform, dataset=None)[source]#

Bases: ContinualModel

Continual learning via Dark Experience Replay.

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

ArgumentParser

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