https://github.com/hyperplasma/hymtsf
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.
https://github.com/hyperplasma/hymtsf
python pytorch time-series-forecasting transformer
Last synced: 3 months ago
JSON representation
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.
- Host: GitHub
- URL: https://github.com/hyperplasma/hymtsf
- Owner: hyperplasma
- License: mit
- Created: 2025-07-27T16:38:18.000Z (10 months ago)
- Default Branch: master
- Last Pushed: 2025-07-28T07:43:09.000Z (10 months ago)
- Last Synced: 2025-09-07T03:43:16.473Z (9 months ago)
- Topics: python, pytorch, time-series-forecasting, transformer
- Language: Python
- Homepage: https://www.hyperplasma.top
- Size: 42 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Hyplus Multivariate Time-Series Forecasting
[Hyperplasma](https://www.hyperplasma.top)
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](https://drive.google.com/drive/folders/1ZOYpTUa82_jCcxIdTmyr0LXQfvaM9vIy), :
* electricity
* ETTh1
* ETTh2
* ETTm1
* ETTm2
* exchange_rate
* national_illness
* traffic
* weather