github google-deepmind/optax v0.1.3
Optax 0.1.3.

latest releases: v0.2.3, v0.2.2, v0.2.1...
2 years ago

What's Changed

  • Do not use None in optax.masked. in #338
  • Implement Adamax and AdamaxW optimizers. in #342
  • Add Kullback-Leibler Divergence Loss by @holounic in #309
  • Add optax.softmax_cross_entropy_with_integer_labels. in #343
  • Publicize private methods in transform in #348
  • Update .pylintrc in #354
  • Support mixture of dtypes for parameters when clipping. in #355
  • Update "jax.tree_util" functions in #370

New Contributors

Full Changelog: v0.1.2...v0.1.3

Don't miss a new optax release

NewReleases is sending notifications on new releases.