awesome-transformer, should classified into Deep Learning。
Transformer is a powerful model applied in sequence to sequence learning. However, when I was using transformer as my baseline in NMT research I found no good & reliable guide to reproduce approximate result as reported in original paper(even official tensor2tensor implementation), which means my research would be unauthentic. I searched on the Internet, found some implementations, obtained some performance-reproducable approaches and other learning materials, which eventually formed this project.
I hope more researchers can benefit from it.
Originally created by @SkyAndCloud on GitHub (Sep 5, 2018).
Original GitHub issue: https://github.com/sindresorhus/awesome/issues/1391
[awesome-transformer](https://github.com/SkyAndCloud/awesome-transformer), should classified into `Deep Learning`。
Transformer is a powerful model applied in sequence to sequence learning. However, when I was using transformer as my baseline in NMT research I found no good & reliable guide to reproduce approximate result as reported in original paper(even official tensor2tensor implementation), which means my research would be unauthentic. I searched on the Internet, found some implementations, obtained some performance-reproducable approaches and other learning materials, which eventually formed this project.
I hope more researchers can benefit from it.
<!-- gh-comment-id:419450391 -->
@sindresorhus commented on GitHub (Sep 7, 2018):
Make sure you follow https://github.com/sindresorhus/awesome/blob/master/pull_request_template.md, then do a pull request.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @SkyAndCloud on GitHub (Sep 5, 2018).
Original GitHub issue: https://github.com/sindresorhus/awesome/issues/1391
awesome-transformer, should classified into
Deep Learning。Transformer is a powerful model applied in sequence to sequence learning. However, when I was using transformer as my baseline in NMT research I found no good & reliable guide to reproduce approximate result as reported in original paper(even official tensor2tensor implementation), which means my research would be unauthentic. I searched on the Internet, found some implementations, obtained some performance-reproducable approaches and other learning materials, which eventually formed this project.
I hope more researchers can benefit from it.
@sindresorhus commented on GitHub (Sep 7, 2018):
Make sure you follow https://github.com/sindresorhus/awesome/blob/master/pull_request_template.md, then do a pull request.