Skip to content

A LSTM implementation with only using basic components of pytorch

Notifications You must be signed in to change notification settings

bombs-kim/handmade_lstm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Handmade LSTM

A LSTM implementation with only using basic components of pytorch. The goal of this project is to offer clean code that is easy to inspect and extend while retaining competitive performance. Arguably, it offers the most clean code that you can find if you are trying to know how LSTM works. Chapter 4 of Supervised Sequence Labelling with Recurrent Neural Networks is recommneded for theoretical background.

demo

Please see demo to see how to use it.

About

A LSTM implementation with only using basic components of pytorch

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published