deepinv.loss#
This package provides a collection of supervised and self-supervised loss functions for training reconstruction networks. Refer to the user guide for more information.
Base class#
User Guide: refer to Training Losses for more information.
Base class for all loss functions. |
Supervised Learning#
User Guide: refer to Supervised Learning for more information.
Standard supervised loss |
Self-Supervised Learning#
User Guide: refer to Self-Supervised Learning for more information.
Measurement consistency loss |
|
Equivariant imaging self-supervised loss. |
|
Multi-operator imaging loss |
|
Multi-operator equivariant imaging. |
|
Neighbor2Neighbor loss. |
|
Measurement splitting loss. |
|
Phase2Phase loss for dynamic data. |
|
Artifact2Artifact loss for dynamic data. |
|
SURE loss for Gaussian noise |
|
SURE loss for Poisson noise |
|
SURE loss for Poisson-Gaussian noise |
|
Total variation loss (\(\ell_2\) norm). |
|
Recorrupted-to-Recorrupted (R2R) Loss |
|
Learns score of noise distribution. |
Adversarial Learning#
User Guide: refer to Adversarial Learning for more information.
Generic GAN discriminator metric building block. |
|
Base generator adversarial loss. |
|
Base discriminator adversarial loss. |
|
Supervised adversarial consistency loss for generator. |
|
Supervised adversarial consistency loss for discriminator. |
|
Unsupervised adversarial consistency loss for generator. |
|
Unsupervised adversarial consistency loss for discriminator. |
|
Reimplementation of UAIR generator's adversarial loss. |
Network Regularization#
User Guide: refer to Network Regularization for more information.
Computes the spectral norm of the Jacobian. |
|
Computes the Firm-Nonexpansiveness Jacobian spectral norm. |
Loss schedulers#
User Guide: refer to Loss schedulers for more information.
Base class for loss schedulers. |
|
Schedule losses at random. |
|
Schedule losses sequentially one-by-one. |
|
Schedule losses sequentially epoch-by-epoch. |
|
Activate losses at specified epoch. |