mridc.collections.reconstruction.models.primaldual package

Submodules

mridc.collections.reconstruction.models.primaldual.pd module

class mridc.collections.reconstruction.models.primaldual.pd.DualNet(num_dual, **kwargs)

Bases: Module

Dual Network for Learned Primal Dual Network.

static compute_model_per_coil(model, data)

Computes model per coil.

Parameters

• model (Model to compute.) –

• data (Multi-coil input.) –

Return type

Multi-coil output.

forward(h, forward_f, g)

Forward pass.

training: bool

class mridc.collections.reconstruction.models.primaldual.pd.PrimalNet(num_primal, **kwargs)

Bases: Module

Primal Network for Learned Primal Dual Network.

forward(f, backward_h)

Forward pass of primal network.

Parameters

• f (Forward function.) –

• backward_h (Backward function.) –

Return type

Primal function.

training: bool

Module contents