Releases: Thinklab-SJTU/pygmtools
Releases · Thinklab-SJTU/pygmtools
0.2.8
0.2.7
What's Changed
- Add progress bar when downloading datsets
- Sort WillowObject data list to facilitate partitioning the training and test set
Full Changelog: 0.2.6...0.2.7
0.2.6
- Update documentation for classic solvers and multi graph solvers
- Support non-batched inputs:
rrwm
,ipfp
,sm
,utils.build_aff_mat
,utils.compute_affinity_score
Full Changelog: 0.2.5...0.2.6
0.2.5
pygmtools 0.2.4
What's Changed
- Paddle support for functions in classic_solvers.py by @Arist12 in #2
- Bug fix for Sinkhorn
- Updated debugging interface for GAMGM
Full Changelog: 0.2.3...0.2.4
pygmtools 0.2.3
- Support CUDA ops for MGM
- Add "device" argument for
from_numpy
- Fix testing script for GAMGM
Full Changelog: 0.2.2...0.2.3
pygmtools 0.2.2
- Add multi-graph matching algorithms (cao, mgm-floyd, gamgm). Now
pytorch
backend is supported. - Add CI support for multi-graph matching
- Bug fixes
Full Changelog: 0.2.1...0.2.2
pygmtools 0.2.1
- Add CI support
- Bug fix: #1
Full Changelog: 0.2.0...0.2.1
pygmtools 0.2.0
We include:
- Benchmark on 5 datasets to handle dataset downloading/processing and evaluation.
- You may also implement other datasets by this API.
- Classic graph matching solvers on pytorch, numpy backend.