Skip to content

0.5.0 Year 2
Compare
Choose a tag to compare
@rflamary rflamary released this 03 Oct 06:46
· 809 commits to master since this release
0.5.0
feaecbe
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.

POT is 2 years old! This release brings numerous new features to the toolbox as listed below but also several bug correction.

Among the new features, we can highlight a non-regularized Gromov-Wasserstein solver, a new greedy variant of sinkhorn, non-regularized, convolutional (2D) and free support Wasserstein barycenters and smooth and stochastic implementation of entropic OT.

POT 0.5 also comes with a rewriting of ot.gpu using the cupy framework instead of the unmaintained cudamat. Note that while we tried to keed changes to the minimum, the OTDA classes were deprecated. If you are happy with the cudamat implementation, we recommend you stay with stable release 0.4 for now.

The code quality has also improved with 92% code coverage in tests that is now printed to the log in the Travis builds. The documentation has also been greatly improved with new modules and examples/notebooks.

This new release is so full of new stuff and corrections thanks to the old and new POT contributors (you can see the list in the readme).

Features

  • Add non regularized Gromov-Wasserstein solver (PR #41)
  • Linear OT mapping between empirical distributions and 90% test coverage (PR #42)
  • Add log parameter in class EMDTransport and SinkhornLpL1Transport (PR #44)
  • Add Markdown format for Pipy (PR #45)
  • Test for Python 3.5 and 3.6 on Travis (PR #46)
  • Non regularized Wasserstein barycenter with scipy linear solver and/or cvxopt (PR #47)
  • Rename dataset functions to be more sklearn compliant (PR #49)
  • Smooth and sparse Optimal transport implementation with entropic and quadratic regularization (PR #50)
  • Stochastic OT in the dual and semi-dual (PR #52 and PR #62)
  • Free support barycenters (PR #56)
  • Speed-up Sinkhorn function (PR #57 and PR #58)
  • Add convolutional Wassersein barycenters for 2D images (PR #64)
  • Add Greedy Sinkhorn variant (Greenkhorn) (PR #66)
  • Big ot.gpu update with cupy implementation (instead of un-maintained cudamat) (PR #67)

Deprecation

Deprecated OTDA Classes were removed from ot.da and ot.gpu for version 0.5 (PR #48 and PR #67). The deprecation message has been for a year here since 0.4 and it is time to pull the plug.

Closed issues

  • Issue #35 : remove import plot from ot/__init__.py (See PR #41)
  • Issue #43 : Unusable parameter log for EMDTransport (See PR #44)
  • Issue #55 : UnicodeDecodeError: 'ascii' while installing with pip
Assets 2
Loading