priors.Laplace

Contents

priors.Laplace#

class bartorch.priors.Laplace#

Bases: Regularizer

\(\ell_1\) norm of a Laplacian-filtered image (BART’s P).

\(\lambda \| L x \|_1\), where \(G = L\) is a 3 x 3 convolution with the kernel [[-1, -2, -1], [-2, 12, -2], [-1, -2, -1]].

Parameters:

  • axes (tuple of int) – Exactly two axes to filter, as indices into the image’s shape.

  • weight (float) – \(\lambda\).

  • joint_axes (int or tuple of int, default=()) – Axes along which entries are thresholded jointly.

Raises:

ValueError – If axes does not name exactly two axes.

Also has the methods and properties of Regularizer.

Contents