selfeeg.losses

This module collects all the losses implemented for the contrastive learning algorithms of the ssl module.

losses.losses module

Functions

barlow_loss	Pytorch implementation of the Barlow Twins loss function as presented in [barlow] .
byol_loss	Simple pytorch implementation of the BYOL loss function presented in [BYOL] .
moco_loss	Simple implementation of the MoCo loss function [moco2].
simclr_loss	simclr_loss computes the normalized temperature-scaled cross entropy loss [NTXent] , which is used in many contrastive learning algorithm.
simsiam_loss	Simple implementation of the SimSiam [simsiam] loss function with the possibility to not normalize tensors.
vicreg_loss	Pytorch implementation of the VICReg loss function [VIC] .