Skip to content

0.99.23
Compare
Choose a tag to compare
@Joao-L-S-Almeida Joao-L-S-Almeida released this 16 Jun 14:18
· 306 commits to main since this release
0.99.23
46b2b76
  • Weights adjusters for balancing the loss function terms are now supported with the state-of-art approaches Learning Rate Annealing (AnnealingWeights) and Inverse Dirichlet (InverseDirichletWeights).
  • The relative loss option (option enabled via the relative=True argument passed to the loss function dictionary) now also deals with null or very small numbers during the optimization stage.
  • A new option for using logarithimic data-driven losses is now enabled via the argument use_data_log=True
Assets 2
Loading