https://github.com/google/wasserstein-dist

tensorflow implementation of the Wasserstein (aka optimal transport) distance
https://github.com/google/wasserstein-dist

Last synced: 2 months ago
JSON representation

tensorflow implementation of the Wasserstein (aka optimal transport) distance

• Host: GitHub
• URL: https://github.com/google/wasserstein-dist
• Owner: google
• License: apache-2.0
• Archived: true
• Created: 2017-09-15T07:56:22.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2021-03-23T15:49:07.000Z (almost 4 years ago)
• Last Synced: 2024-08-03T01:38:31.529Z (6 months ago)
• Language: Python
• Homepage:
• Size: 11.7 KB
• Stars: 71
• Watchers: 7
• Forks: 17
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
### wasserstein-dist 

============================

wasserstein-dist is a tensorflow implementation of the Wasserstein 

(aka optimal transport) distance between a fixed set of data points 

and a probability distribution (from which one can sample). 

It can also be used to compute the distance between to points sets,

but it is not optimized for this purpose. 

The implementation follows the semi-dual Algorithms 2 in [Genevay Aude, 

Marco Cuturi, Gabriel Peyre, Francis Bach, "Stochastic Optimization for 

Large-scale Optimal Transport", NIPS 2016]. 

---

This is not an official Google product.