XDER RPC STAR

Arguments

Options

--alphafloat

Help: Penalty weight.

• Default: None

--betafloat

Help: Penalty weight.

• Default: None

--p_stepsint

Help: None

• Default: 1

--p_lamfloat

Help: None

• Default: 0.01

--p_gammafloat

Help: how far we can go from original weights

• Default: 0.05

--gammafloat

Help: None

• Default: 0.85

--etafloat

Help: None

• Default: 0.001

--mfloat

Help: None

• Default: 0.3

--clip_gradnone_or_float

Help: Clip gradient norm (default: None, no clipping)

• Default: None

--align_bnint

Help: Use BatchNorm alignment

• Default: 0

• Choices: 0, 1

--n_rpc_headsint

Help: N Heads for RPC

• 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.xder_rpc_star.XDerRPCSTAR(backbone, loss, args, transform, dataset=None)

Bases: ContinualModel

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

NAME: str = 'xder_rpc_star'

end_task(dataset)

forward(x)

static get_parser(parser)

Return type:

ArgumentParser

observe(inputs, labels, not_aug_inputs, epoch=None)

update_logits(old, new, gt, task_start, n_tasks=1)

Functions

models.xder_rpc_star.dsimplex(num_classes=10)

models.xder_rpc_star.dsimplex(num_classes=10)