Skip to content

Releases: mathisgerdes/bijx

v1.2.1

11 Mar 21:50

Choose a tag to compare

  • Improved API consistency in accepting and passing **kwargs to constituent densities and transformations.
  • Fixed minor sign error in Fourier scaling layer (constant offset in log-density; irrelevant for training).
  • Bump minimum python version as required by flax.

Full Changelog: v1.2.0...v1.2.1

v1.2.0

19 Jan 08:56

Choose a tag to compare

Add analytic bijections and radial flows, including short tutorial.

Full Changelog: v1.1.3...v1.2.0

v1.1.3

10 Dec 21:15

Choose a tag to compare

Add SDE solve to diffrax wrapper and small bug fix.

Full Changelog: v1.1.2...v1.1.3

v1.1.2

30 Nov 14:30

Choose a tag to compare

Release for JOSS paper. Corrected minor typos.

Full Changelog: v1.1.1...v1.1.2

v1.1.1

25 Nov 13:18

Choose a tag to compare

Update to latest flax version:

  • Deprecates .value on nnx.Variable
  • New nnx.dataclass

Full Changelog: v1.1.0...v1.1.1

v1.1.0

15 Nov 16:10

Choose a tag to compare

Crouch-Grossmann Integration API Refactor

  • Make it easier to select various choices in the integration algorithm (e.g. enabling projection onto tangent space)
  • Enhanced code clarity and future extensibility

Flax Framework Migration

  • Migrated from flax.struct.dataclass to newer nnx.Pytree API

Minor improvements to batch handling and bug fixes.

Full Changelog: v1.0.2...v1.1.0

v1.0.2

26 Sep 13:45

Choose a tag to compare

  • Bug fixes (primarily for GMM)
  • Fix various compatibility issues with newest flax version.

Full Changelog: v1.0.1...v1.0.2

v1.0.1

07 Sep 05:35

Choose a tag to compare

  • Added general multivariate and diagonal gaussian distributions.
  • Added general mixture of (the same kind of) distributions.
  • Minor improvements to documentation and added GMM tutorial.

Full Changelog: v1.0.0...v1.0.1

Initial stable release

25 Aug 12:13

Choose a tag to compare

JAX-based normalizing flows and bijections library, with special focus on physics research. Features continuous normalizing flows, matrix Lie group operations, and flexible architecture blocks. Built on Flax NNX with focus on research flexibility and composability.