TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

From GAN to WGAN (2017)

67 pointsby rouliover 6 years ago

1 comment

nlover 6 years ago
If anyone is looking for a good project, alternate Wasserstein distance&#x2F;EMD solvers would be a good place to start.<p>AFAIK everyone (eg, pyemd, gensim, textacy) uses wrappers around the EMD solver from <a href="http:&#x2F;&#x2F;ofirpele.droppages.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;ofirpele.droppages.com&#x2F;</a>, which is a zip file from some time in 2008. The limits on performance mean it can&#x27;t practically be used in things like interactive nearest neighbor calculations (FAISS, nmslib, annoy etc)
评论 #17850655 未加载
评论 #17851652 未加载
评论 #17854138 未加载