LossFunctions.jl
LossFunctions.jl copied to clipboard
JuliaML
Julia package of loss functions for machine learning.
It seems I can't use the loss functions in this package for either SparseVectors or Flux's tracked vectors. Is there a good reason why a general `AbstractVector{ using LossFunctions julia>...
I would like to add a simple Hausdorff Loss as proposed in (DOI: 10.1109/TMI.2019.2930068) It approximates the Hausdorff distance to allow for direct minimization of the HD during training ```julia...
Feature Request: Add [quadratic weighted kappa](https://www.kaggle.com/c/petfinder-adoption-prediction#evaluation) loss function.
Dear all, I would like to propose a major refactoring of the codebase to *simplify* future additions and generalizations, and to facilitate future contributions. I think we are overusing macros...
Hi all and thanks for the this very useful package ! It could be helpful to get in addition to the islipschitzcont attribute, another attribute that gives the value of...
Maximizing the expected log posterior density (ELPD) is a common objective function in Bayesian inference and Bayesian neural networks, and I'd be interested in having it as a loss function...
Perhaps I'm missing something, but this does not appear to exist at present. For most losses with a parameter, you access using property, as in ```julia loss = HuberLoss(0.5) julia>...
This looks like a bug to me: ```julia julia> y = rand(3); yhat = rand(3); w = rand(3); julia> value(L1DistLoss(), y, yhat, AggMode.WeightedMean(w, normalize=false)) 0.4515037807304132 julia> value(L1DistLoss(), y, yhat, AggMode.WeightedSum(w,...
One bridge we have to cross sooner or later are multiclass problems. There are mutliclass extensions or formulations for a couple of losses that we have. A particular interesting example...
