https://github.com/armhold/rnn

Recurrent Neural Network in Go
https://github.com/armhold/rnn

Last synced: 3 months ago
JSON representation

Recurrent Neural Network in Go

• Host: GitHub
• URL: https://github.com/armhold/rnn
• Owner: armhold
• Created: 2016-04-16T22:34:18.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2016-06-11T14:45:21.000Z (about 8 years ago)
• Last Synced: 2023-07-10T18:08:41.648Z (12 months ago)
• Language: Go
• Homepage:
• Size: 447 KB
• Stars: 13
• Watchers: 3
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Lists

• my-awesome-stars - armhold/rnn - Recurrent Neural Network in Go (Go)

README

        
# RNN - a Recurrent Neural Network in Go

This is more or less a straight translation of Andrej Karpathy's

[Recurrent Neural Network code](https://gist.github.com/karpathy/d4dee566867f8291f086) from Python to Go. See

http://karpathy.github.io/2015/05/21/rnn-effectiveness for more information.

I have attempted to translate it faithfully, even down to the level of preserving variable names

(many of which are somewhat... terse) and his comment text. The one major change I did introduce is

code for checkpointing the model; this is primarily implemented in persistence.go.

Any errors here are my own, and not Karpathy's. Corrections welcome.

## How to use it

1. `$ go get github.com/armhold/rnn/...`

1. `$ cd $GOPATH/src/github.com/armhold/rnn`

1. `$ rnn -i input.txt`

This will run the network on a small corpus of Shakespeare text. After a few thousand iterations,

you should start seeing output that looks superficially like a Shakespeare play.