deepmr.optim.ADMMStep#
- class deepmr.optim.ADMMStep(*args: Any, **kwargs: Any)[source]#
Alternate Direction of Multipliers Method step.
This represents propagation through a single iteration of a ADMM 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(s) for plug-n-play restoration.
- Type:
Iterable(Callable)
- trainable#
If
True
, gradient update step is trainable, otherwise it is not. The default isFalse
.- Type:
bool, optional
- ndim#
Number of spatial dimensions of the problem for inner data consistency step. It is used to infer the batch axes. If
AHA
is adeepmr.linop.Linop
operator, this is inferred fromAHA.ndim
andndim
is ignored.- Type:
int, optional
Methods
__init__
(step, AHA, AHy, D[, trainable, ...])forward
(input)