Skip to content

A PyTorch-based toolkit for Multivariate Time Series Forecasting, featuring state-of-the-art models like PatchTST and our new architectures. Offers modular design for easy extension and full pipeline.

License

Notifications You must be signed in to change notification settings

hyperplasma/HyMTSF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Hyplus Multivariate Time-Series Forecasting

Hyperplasma

A collection of various Multivariate Time-Series Forecasting (MTSF) models. Might be used in contrast experiments later.

Models

All implemented models are listed below (some of them are still WIP):

  • PatchTST
  • Crossformer
  • DeformTime
  • iTransformer
  • DLinear
  • PatchTST

Datasets

All datasets are from Autoformer, :

  • electricity
  • ETTh1
  • ETTh2
  • ETTm1
  • ETTm2
  • exchange_rate
  • national_illness
  • traffic
  • weather

About

A PyTorch-based toolkit for Multivariate Time Series Forecasting, featuring state-of-the-art models like PatchTST and our new architectures. Offers modular design for easy extension and full pipeline.

Topics

Resources

License

Stars

Watchers

Forks