Skip to content

A dual stage attention LSTM network for time series prediction

Notifications You must be signed in to change notification settings

vatch123/DA_RNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DA_RNN

A dual stage attention LSTM network used for time series prediction.

This is an implementation of the paper for my use case of predicting solar irradiation values. The input sequence is multivariate with various meterological parameters.

The model code is heavily inspired by this blogpost by Chandler Zuo.

This code has added functionality:

  • To define various training runs with different set of hyperparameters
  • Keep track of all the runs during training using tensorboard

About

A dual stage attention LSTM network for time series prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages