NormLimitRegularizer
- class NormLimitRegularizer(*, weight=1.0, apply_only_once=False, dim=-1, p=2.0, power_norm=True, max_norm=1.0, **kwargs)[source]
Bases:
Regularizer
A regularizer which formulates a soft constraint on a maximum norm.
Initialize the regularizer.
- Parameters
weight (
float
) – The relative weight of the regularizationapply_only_once (
bool
) – Should the regularization be applied more than once after reset?dim (
Optional
[int
]) – 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 insteadmax_norm (
float
) – the maximum norm until which no penalty is addedkwargs – additional keyword-based parameters passed to
Regularizer.__init__()
Methods Summary
forward
(x)Compute the regularization term for one tensor.
Methods Documentation