Skip to content
/ GRU Public

A C++ implementation of a 3 layer Gated Recurrent Unit (GRU) using no libraries other than Eigen for Matrices.

Notifications You must be signed in to change notification settings

kirit93/GRU

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is an implementation of a GRU in C++ using no libraries other than Eigen for Matrices. This is a barebones implementation that uncovers the complexity of backpropagation. All equations have been derived and implemented.

Create a folder for weights called Weights

Usage -

make
./train
./test `epoch_number` `loss`

e.g. ./test 66 0.397798

About

A C++ implementation of a 3 layer Gated Recurrent Unit (GRU) using no libraries other than Eigen for Matrices.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published