fStep#

class deepinv.optim.optim_iterators.fStep(g_first=False, **kwargs)[source]#

Bases: Module

Module for the single iteration steps on the data-fidelity term \(f\).

Parameters:

g_first (bool) – If True, the algorithm starts with a step on g and finishes with a step on f. Default: False.
kwargs – Additional keyword arguments.

Examples using `fStep`:#

PnP with custom optimization algorithm (Condat-Vu Primal-Dual)

PnP with custom optimization algorithm (Condat-Vu Primal-Dual)

Learned Primal-Dual algorithm for CT scan.

Learned Primal-Dual algorithm for CT scan.