OrthogonalityRegularizer

class OrthogonalityRegularizer(*, weight=1.0, apply_only_once=True, epsilon=1e-05, **kwargs)[source]

A regularizer for the soft orthogonality constraints from [wang2014].

Initialize the regularizer.

Parameters:

weight (float) – The relative weight of the regularization
apply_only_once (bool) – Should the regularization be applied more than once after reset?
epsilon (float) – a small value used to check for approximate orthogonality
kwargs – additional keyword-based parameters passed to Regularizer.__init__()

Methods Summary

`forward`(x)	Compute the regularization term for one tensor.
`update`(*tensors)	Update the regularization term based on passed tensors.

Methods Documentation

Compute the regularization term for one tensor.

update(*tensors)[source]

Update the regularization term based on passed tensors.