bartorch.prox.Regularizer#

class bartorch.prox.Regularizer#

One of BART’s regularization terms.

A term holds the proximal operator and transform BART’s opt_reg_configure builds for it, per image shape, and hands them to a solver as they are: solving twice with a term builds nothing the second time.

kind#

BART’s letter for the term, as pics -R writes it.

Type:

str

axes#

Axes the term works over, as indices into the image’s shape.

Type:

tuple of int

joint_axes#

Axes along which the term acts jointly.

Type:

tuple of int

count#

Entries an NIHT term keeps; zero for every other term.

Type:

int

__init__()#

Methods

__init__()

apply_transform(x[, image_shape, mode])

This term's transform applied to x, without making an operator of it.

build(shape)

The BART operator for this term over an image of C-order shape.

prox(x[, gamma, image_shape])

prox_{gamma f}(x), the operator BART's solvers call.

prox_shape(image_shape)

The C-order shape this term's proximal operator works on.

rewind(image_shape)

Put this term's own random generator back to where it started.

transform(image_shape)

The operator BART puts in front of this term's proximal operator.

transform_is_identity(image_shape)

Whether that transform is the identity, as BART decides it.

Attributes