Age | Commit message (Collapse) | Author |
|
* Pass warn argument downstream in sinkhorn2 method.
* releases.md
* Fix unittest.
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
empirical_sinkhorn_divergence (#422)
* fix stopThr hardcoded in some places
* added fix documentation in RELEASES.Md
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* bug solve
* releases.md
|
|
* new API for OT solver
* use itertools for product of parameters
* add tests for result class
* add tests for result class
* add tests for result class last time?
* add sinkhorn
* make partial OT bckend compatible
* add TV as unbalanced flavor
* better tests
* make smoth backend compatible and add l2 tregularizatio to solve
* add reularizedd unbalanced
* add test for more complex attibutes
* add test for more complex attibutes
* add generic unbalaned solver and implement it for ot.solve
* add entropy to possible regularization
* star of documentation for ot.solv
* weird new pep8
* documenttaion for function ot.solve done
* pep8
* Update ot/solvers.py
Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>
* update release file
* Apply suggestions from code review
Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>
* add test NotImplemented
* pep8
* pep8gcmp pep8!
* compute kl in backend
* debug tensorflow kl backend
Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>
|
|
* correct bug in DA l1lp with log
* better tests and speedup with smaller dataset size
* remove jax for log test
* remove trndorflow for log test
* pep8!
|
|
* Docstrings of weak.py updated
* releases.md
|
|
* Numpy ccompiler deprecation handled with setuptools ccompiler
* Remove useless OMP Macro, already provides _OPENMP
* RELEASES.md
* Remove forgotten temporary bug added for logging purposes
|
|
* Bug solve
* Releases.md updated
* pep8
* attempt to solve docs building bug
* releases.md
|
|
* add option for preper subsections
* cleanup dodecov ignore
* cleanup dodecov ignore
|
|
* skip tets if not torch installed
* update release.md
|
|
* Solve example throwing an error when executed on a GPU
* add PR to releases.md
* update pep8 command
* pep8
|
|
* Adding function for computing Sinkhorn Free Support barycenters
* Adding exampel on Free Support Sinkhorn Barycenter
* Fixing typo on free support sinkhorn barycenter example
* Adding info on new Free Support Barycenter solver
* Removing extra line so that code follows pep8
* Fixing issues with pep8 in example
* Correcting issues with pep8 standards
* Adding tests for free support sinkhorn barycenter
* Adding section on Sinkhorn barycenter to the example
* Changing distributions for the Sinkhorn barycenter example
* Removing file that should not be on the last commit
* Adding PR number to REALEASES.md
* Adding new contributors
* Update CONTRIBUTORS.md
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* Two lines added in the function emd2 to ensure that the distributions have the same mass (same as it already was in the function emd).
* The same mass test has been moved inside the function f(b) to be compatible with emd2 with multiple b.
* Test added.
The function test_emd_dimension_and_mass_mismatch (in test/test_ot.py) has been modified to check for mass mismatch with emd2.
* Add PR in releases.md
* Merge and add PR in releases.md
* Add name in contributors.md
* Correction contribution in contributors.md
* Move test on mass outside of functions f(b)
* Update doc of emd and emd2
Co-authored-by: Camille Le Coz <clecoz@camelot.ipsl.polytechnique.fr>
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* avoid overflow on openmp version of emd solver
* monothread version updated
* Fixed typo in readme
* added PR in releases
* typo in releases.md
* added a precision to releases.md
* added a precision to releases.md
* correct readme
* forgot to cast
* lower error
|
|
* Correct test_mm_convergence for cupy
* Fix bug where number of iterations is limited to 2^31
* Update RELEASES.md
* Replace size_t with long long
* Use uint64_t instead of long long
|
|
typo in releases
|
|
test (#376)
* GWB first solver version
* tests + example for gwb (untested) + free_bar doc fix
* improved doc, fixed minor bugs, better example visu
* minor doc + visu fixes
* plot GWB pep8 fix
* fixed partial gromov test reproductibility
* added an animation for the GWB visu
* added PR num
* minor doc fixes + better gwb logo
* GWB graphical tweaks + better seed method for partial gromov test
* fixed PR number
* refixed seed issue
* seed fix fix fix
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* Solve bug
* Update release file
|
|
* GWB first solver version
* tests + example for gwb (untested) + free_bar doc fix
* improved doc, fixed minor bugs, better example visu
* minor doc + visu fixes
* plot GWB pep8 fix
* fixed partial gromov test reproductibility
* added an animation for the GWB visu
* added PR num
* minor doc fixes + better gwb logo
|
|
* release text and number
* add examples in release fil build wheels
* switch gallery to release
* add much needed contributors file
* debug circleci
* une line of logos
* working logo
* back to stable sphinx galery
|
|
* center gradients for mass of emd2 and gw2
* debug fgw gradient
* debug fgw
|
|
* bugfix
* update refs partial OT
* fixes small typos in plot_partial_wass_and_gromov
* fix small bugs in partial.py
* update README
* pep8 bugfix
* modif doctest
* fix bugtests
* update on test_partial and test on the numerical precision on ot/partial
* resolve merge pb
* Delete partial.py
* update unbalanced: mm algo+plot
* update unbalanced: mm algo+plot
* update unbalanced: mm algo+plot
* update unbalanced: mm algo+plot
* update unbalanced: mm algo+plot
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* add test mm algo unbalanced OT
* update unbalanced: mm algo+plot
* update unbalanced: mm algo+plot
* update releases.md with new MM UOT algorithms
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* remove all cpu submodule and tests
* speedup tests gromov
|
|
* add transparent color logo
* add transparent color logo
* move screenkhorn
* move stochastic and install ffmpeg on circleci
* try something
* add sudo
* install ffmpeg before python
* cleanup examples
* test svg scrapper
* add animation for reg path
* better example OT sivergence
* update ttles and add plots
* update free support
* proper figure indexes
* have less frame sin animation
* update readme and release file
* add tests for python 3.10
|
|
or regularized OT (#360)
* add losses and plan computations and exmaple for dual oiptimization
* pep8
* add nice exmaple
* update awesome example stochasti dual
* add all tests
* pep8 + speedup exmaple
* add release info
|
|
* add gfactored ot
* pep8 and add doc
* add exmaple for factotred OT
* final number of PR
* correct test on backends
* remove useless loss
* better tests
|
|
* First draft
* Add matrix inverse and square root to backend
* Eigen decomposition for older versions of pytorch (1.8.1 and older)
* Corrected eigen decomposition for pytorch 1.8.1 and older
* Spectral theorem is a thing
* Optimization
* small optimization
* More functions converted
* pep8
* remove a warning and prepare torch meshgrid for future torch release (which will change default indexing)
* dots and pep8
* Meshgrid corrected for older version and prepared for future versions changes
* New backend functions
* Base transport
* LinearTransport
* All transport classes + pep8
* PR added to release file
* Jcpot barycenter test
* unbalanced with backend
* pep8
* bug solve
* test of domain adaptation with backends
* solve bug for tic toc & macos
* solving scipy deprecation warning
* solving scipy deprecation warning attempt2
* solving scipy deprecation warning attempt3
* A warning is triggered when a float->int conversion is detected
* bug solve
* docs
* release file updated
* Better handling of float->int conversion in EMD
* Corrected test for is_floating_point
* docs
* release file updated
* cupy does not allow implicit cast
* fromnumpy
* added test
* test da tf jax
* test unbalanced with no provided histogram
* using type_as argument in unif function correctly
* pep8
* transport plan cast in emd changed behaviour, now trying to cast as histogram's dtype, defaulting to cost matrix
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* add logo code and logo to doc
* update release file
|
|
* Resolves gromov wasserstein backward bug
* release file updated
|
|
* propreer links in release file in documentation
* add pr in release file
|
|
* Configure setup to compile against oldest supported numpy version using the meta-package: https://pypi.org/project/oldest-supported-numpy/ -
* Set minimum Python requirement to `>=3.7` in setup.py since !328 removed Python 3.6 support
* Fix typo in pyproject.toml -
* Update setup.py
* Update setup.py and
* build wheels
* remove install dependencies for wheels building and build wheels
* Apply suggestions from code review
Co-authored-by: David M. Ghiurco <9147386+davidghiurco@users.noreply.github.com>
* correct timing test add info in release file and build wheels
* pep8 and
Co-authored-by: David Ghiurco <9147386+davidghiurco@users.noreply.github.com>
|
|
* add fgw dictionary learning feature
* add fgw dictionary learning feature
* plot gromov wasserstein dictionary learning
* Update __init__.py
* fix pep8 errors exact E501 line too long
* fix last pep8 issues
* add unitary tests for (F)GW dictionary learning without using autodifferentiable functions
* correct tests for (F)GW dictionary learning without using autodiff
* correct tests for (F)GW dictionary learning without using autodiff
* fix docs and notations
* answer to review: improve tests, docs, examples + make node weights optional
* fix pep8 and examples
* improve docs + tests + thumbnail
* make example faster
* improve ex
* update README.md
* make GDL tests faster
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
* add info in release file
* update tests
* pep8
* add weak OT example
* update plot in doc
* correction ewample with empirical sinkhorn
* better thumbnail
* comment from review
* update documenation
|
|
* backend version barycenter
* new tests
* cleanup release file and doc
* f*ing pep8
* remove unused variable
|
|
* [MRG] Implement Sinkhorn in log-domain for WDA
* for small values of the regularization parameter (reg) the current implementation runs into numerical issues (nans and infs)
* this can be resolved by using log-domain implementation of the sinkhorn algorithm
* Add feature to RELEASES and contributor name
* Add 'sinkhorn_method' parameter to WDA
* use the standard Sinkhorn solver by default (faster)
* use log-domain Sinkhorn if asked by the user
Co-authored-by: Jakub Zadrożny <jz@qed.ai>
Co-authored-by: Rémi Flamary <remi.flamary@gmail.com>
|
|
PyTorch) (#338)
* Not instantiating `ValFunction`
`ValFunction` should not be instantiated since `autograd` functions are
supposed to only ever use static methods. This solves a warning message
raised by PyTorch.
* Updated release information
* Fixed PR number
|
|
* change version and add minigallery in quickstart guide
* remove ot.gpu from documentation because it is deprecated and bacckends should be used
* start 0.8.2dev and description in releases.md
* typo for gallery sinkhorn2
* test better doc update for files in .githib folder
|
|
* update ersion and change doc build
* update release file
* debug release of doc
* set version number to 0.8.1.0
|
|
* update delease file and add it to doc ith mystè_parser
* typos in release file
* update PR template
* test debug doc build
* test debug doc build
* wrog circleci
* set proper version number
* add numpy 1.20 constraint
* remove python 3.6 deprecated in december
* add python 3.10
* debug pip on windows
* proper yml
* remoe 3.10 becauqe of troch
* next try
* try distutils
* back
* try something
* new stuf
* debug yaml
* test back to old vriso f numpy
* try something
* windows is worksing?
* proper version numpy
* update release file
|
|
* update delease file and add it to doc ith mystè_parser
* typos in release file
* update PR template
* test debug doc build
* test debug doc build
* wrog circleci
* set proper version number
* add numpy 1.20 constraint
* remove python 3.6 deprecated in december
* add python 3.10
* debug pip on windows
* proper yml
* remoe 3.10 becauqe of troch
* next try
* try distutils
* back
* try something
* new stuf
* debug yaml
* test back to old vriso f numpy
* try something
* windows is worksing?
|
|
* update delease file and add it to doc ith mystè_parser
* typos in release file
* update PR template
|
|
* working on release
* test circleci
* try again
* cleanup circle ci run
* add all PR and releant Issues
* update doc
* thanks idris
* update version + add pyproject.toml
* test pyproject.toml
* revert tests
* build wheels
* use windows-latest for tests
* add tests python 3.10
* build all whels
* all versions
* build all wheels
* build all wheels
* cleanup pep8 and minimal acions
* forst shot text release
* bettr text
* stuff
* release text updated
* update manifest to allow build from source
* update doc again
* update release
|
|
|
|
Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>
|
|
Co-authored-by: Alexandre Gramfort <alexandre.gramfort@m4x.org>
|
|
|
|
|
|
|
|
|
|
|