demo_mri_model

deepinv.utils.demo.demo_mri_model(denoiser=None, num_iter=3, device='cpu')

Demo MRI reconstruction model for use in relevant examples.

As a reconstruction network, we use an unrolled network (half-quadratic splitting) with a trainable denoising prior based on the DnCNN architecture, as an example of a model-based deep learning architecture from MoDL.

Parameters:

• denoiser (Denoiser, torch.nn.Module) – backbone denoiser model. If None, uses deepinv.models.DnCNN

• num_iter (int) – number of unfolded layers (“cascades”), defaults to 3.

• device (str, torch.device) – device

Return torch.nn.Module:

model

Return type:

Reconstructor

Examples using demo_mri_model:

Tour of MRI functionality in DeepInverse

Tour of MRI functionality in DeepInverse

Self-supervised MRI reconstruction with Artifact2Artifact

Self-supervised MRI reconstruction with Artifact2Artifact

Self-supervised learning with Equivariant Imaging for MRI.

Self-supervised learning with Equivariant Imaging for MRI.