Metadata-Version: 2.4
Name: diresa-torch
Version: 1.2.2
Summary: Diresa - distance-regularized siamese twin autoencoder
Project-URL: Homepage, https://gitlab.com/etrovub/ai4wcm/public/diresa-torch
Project-URL: Issues, https://gitlab.com/etrovub/ai4wcm/public/diresa-torch/-/issues
Author-email: Lars Bonnefoy <lars.bonnefoy@vub.be>, Janne Bouillon <janne.lisa.bouillon@vub.be>, Geert De Paepe <geert.de.paepe@vub.be>
License-File: LICENSE
Keywords: climate,learning,machine,pytorch,weather
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Requires-Dist: torch>=2.1
Description-Content-Type: text/markdown

# *DIRESA-Torch*


### Overview

*DIRESA-Torch* is a Python package for dimension reduction based on 
[PyTorch](https://pytorch.org). The distance-regularized 
Siamese twin autoencoder architecture is designed to preserve distance 
(ordering) in latent space while capturing the non-linearities in
the datasets.


### Install *DIRESA-Torch*

Install *DIRESA-Torch* with the following command:

``` bash
  pip install diresa-torch
```

### Documentation

The *DIRESA* documentation can be found on [Read the Docs](https://diresa-torch.readthedocs.io)

### Paper

The *DIRESA* paper can be found [here](https://journals.ametsoc.org/view/journals/aies/4/3/AIES-D-24-0034.1.xml)