deepmr.optim.PGDStep#
- class deepmr.optim.PGDStep(*args: Any, **kwargs: Any)[source]#
Proximal Gradient Method step.
This represents propagation through a single iteration of a Proximal Gradient Descent algorithm; can be used to build unrolled architectures.
- AHA#
Normal operator AHA = AH * A.
- Type:
Callable | torch.Tensor
- Ahy#
Adjoint AH of measurement operator A applied to the measured data y.
- Type:
- D#
Signal denoiser for plug-n-play restoration.
- Type:
Callable
- trainable#
If
True
, gradient update step is trainable, otherwise it is not. The default isFalse
.- Type:
bool, optional
Methods
__init__
(step, AHA, AHy, D[, trainable, tol])check_convergence
(output, input, step)forward
(input[, q])