NormLimitRegularizer

class NormLimitRegularizer(*, weight: float = 1.0, apply_only_once: bool = False, dim: int | None = -1, p: float = 2.0, power_norm: bool = True, max_norm: float = 1.0, **kwargs)

Bases: Regularizer

A regularizer which formulates a soft constraint on a maximum norm.

Initialize the regularizer.

Parameters:

• weight (Tensor) – The relative weight of the regularization

• apply_only_once (bool) – Should the regularization be applied more than once after reset?

• dim (int | None) – the dimension along which to calculate the Lp norm, cf. powersum_norm()

• p (float) – the parameter \(p\) of the Lp norm, cf. powersum_norm()

• power_norm (bool) – whether to use the \(p\) power of the norm instead

• max_norm (float) – the maximum norm until which no penalty is added

• kwargs – additional keyword-based parameters passed to Regularizer.__init__()

Methods Summary

forward(x)

Compute the regularization term for one tensor.

Methods Documentation

forward(x: Tensor) → Tensor

Compute the regularization term for one tensor.

Parameters:

x (Tensor)

Return type:

Tensor