Bregman_ICNN

class deepinv.optim.bregman.Bregman_ICNN(forw_model, conj_model=None)[source]

Bases: Bregman

Module for the using a deep ICNN as Bregman potential.

conjugate(x)[source]

Computes the convex conjugate potential.

Parameters:: x (torch.Tensor) – Variable \(x\) at which the conjugate is computed.
Returns:: (torch.tensor) conjugate potential \(\phi^*(y)\).

fn(x)[source]

Computes the Bregman potential.

Parameters:: x (torch.Tensor) – Variable \(x\) at which the potential is computed.
Returns:: (torch.tensor) potential \(\phi(x)\).