Loss

This package contains popular training losses for supervised and self-supervised learning, which are especially designed for inverse problems.

Introduction

All losses inherit from the base class deepinv.loss.Loss(), which is a meth:torch.nn.Module.

deepinv.loss.Loss

Base class for all loss/metric functions.

>>> import torch
>>> import deepinv as dinv
>>> loss = dinv.loss.SureGaussianLoss(.1)
>>> physics = dinv.physics.Denoising()
>>> x = torch.ones(1, 3, 16, 16)
>>> y = physics(x)
>>> model = dinv.models.DnCNN()
>>> x_net = model(y)
>>> l = loss(x_net=x_net, y=y, physics=physics, model=model) # self-supervised loss, doesn't require ground truth x

Supervised Learning

Use a dataset of pairs of signals and measurements (and possibly information about the forward operator), i.e., they can be written as \(\mathcal{L}(x,\inverse{y})\).

deepinv.loss.SupLoss

Standard supervised loss

Self-Supervised Learning

Use a dataset of measurement data alone (and possibly information about the forward operator), i.e., they can be written as \(\mathcal{L}(y,\inverse{y})\) and take into account information about the forward measurement process.

`deepinv.loss.MCLoss`	Measurement consistency loss
`deepinv.loss.EILoss`	Equivariant imaging self-supervised loss.
`deepinv.loss.MOILoss`	Multi-operator imaging loss
`deepinv.loss.Neighbor2Neighbor`	Neighbor2Neighbor loss.
`deepinv.loss.SplittingLoss`	Measurement splitting loss.
`deepinv.loss.SureGaussianLoss`	SURE loss for Gaussian noise
`deepinv.loss.SurePoissonLoss`	SURE loss for Poisson noise
`deepinv.loss.SurePGLoss`	SURE loss for Poisson-Gaussian noise
`deepinv.loss.TVLoss`	Total variation loss (\(\ell_2\) norm).
`deepinv.loss.R2RLoss`	Recorrupted-to-Recorrupted (R2R) Loss

Metrics

Metrics are generally used to evaluate the performance of a model. Some of them can be used as training losses as well.

`deepinv.loss.PSNR`	Peak Signal-to-Noise Ratio (PSNR) metric.
`deepinv.loss.SSIM`	Structural Similarity Index (SSIM) metric.
`deepinv.loss.LPIPS`	Learned Perceptual Image Patch Similarity (LPIPS) metric.
`deepinv.loss.NIQE`	Natural Image Quality Evaluator (NIQE) metric.

Transforms

This submodule contains different transforms which can be used for data augmentation or together with the equivariant losses.

`deepinv.transform.Rotate`	2D Rotations.
`deepinv.transform.Shift`	Fast integer 2D translations.
`deepinv.transform.Scale`	2D Scaling.

Network Regularization

These losses can be used to regularize the learned function, e.g., controlling its Lipschitz constant.

`deepinv.loss.JacobianSpectralNorm`	Computes the spectral norm of the Jacobian.
`deepinv.loss.FNEJacobianSpectralNorm`	Computes the Firm-Nonexpansiveness Jacobian spectral norm.

Utils

A set of popular distances that can be used by the supervised and self-supervised losses.

deepinv.loss.LpNorm

\(\ell_p\) metric for \(p>0\).