Skip to content

0.6.0
Compare
Choose a tag to compare
@wdevazelhes wdevazelhes released this 01 Jul 10:03
· 41 commits to master since this release
v0.6.0
3e1af68
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

This release features various fixes and improvements, as well as a new triplet-based algorithm, SCML (see http://researchers.lille.inria.fr/abellet/papers/aaai14.pdf), and an associated Triplets API. Triplets-based metric learning algorithms are used in settings where we have an "anchor" sample that we want to be closer with a "positive" sample than with a "negative" sample. Consistently with related packages like scikit-learn, we have also dropped support for Python 2 and Python 3.5.

New algorithms

  • Add Sparse Compositional Metric Learning (SCML) (#278)

General updates on the package

  • Drop support for python 2 and python 3.5 (#291)
  • Add the Triplets API (#279)
  • Solve issues in the documentation (#265, #266, #271, #274, #280)
  • Allow installation from conda (#283)
  • Fix covariance initialization when matrix is not invertible (#277)
  • Add more robusts checks that an estimator is fitted (#267)

Improvements to existing algorithms

  • Improve LMNN's verbose (#253)
  • Fix chunk generation in RCA (#254, #263)
Assets 2
Loading