LpRegularizer
- class LpRegularizer(*, weight=1.0, apply_only_once=False, dim=-1, normalize=False, p=2.0, **kwargs)[source]
Bases:
RegularizerA simple L_p norm based regularizer.
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.lp_norm()normalize (
bool) – whether to normalize the norm by the dimension, cf.lp_norm()p (
float) – the parameter \(p\) of the Lp norm, cf.lp_norm()kwargs – additional keyword-based parameters passed to
Regularizer.__init__()
Attributes Summary
The default strategy for optimizing the LP regularizer's hyper-parameters
Methods Summary
forward(x)Compute the regularization term for one tensor.
Attributes Documentation
- hpo_default: ClassVar[Mapping[str, Any]] = {'weight': {'high': 1.0, 'low': 0.01, 'scale': 'log', 'type': <class 'float'>}}
The default strategy for optimizing the LP regularizer’s hyper-parameters
Methods Documentation