Metadata-Version: 2.1
Name: spectralLayersPyTorch
Version: 0.989
Summary: PyTorch NN based trainable spectral linear layers
Home-page: UNKNOWN
Author: Angela Botros & Narayan Schuetz
Author-email: narayan.schuetz@artorg.unibe.ch
License: MIT
Platform: UNKNOWN
Description-Content-Type: text/markdown
Requires-Dist: torch
Requires-Dist: numpy

## SpectralLayersPyTorch
Trainable linear spectral layers for PyTorch

Implements trainable spectral layers for PyTorch that can be initialized as 1-D & 2-D DCT and DFT transformations as shown in [paper](https://arxiv.org/abs/1911.05045).

## Install
The package can be installed as follows:

    pip install spectral

or

    pip install git+https://github.com/NarayanSchuetz/SpectralLayersPyTorch.git


## Attribution

```
@misc{alberti2019trainable,
      title={Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks}, 
      author={Michele Alberti and Angela Botros and Narayan Schuez and Rolf Ingold and Marcus Liwicki and Mathias Seuret},
      year={2019},
      eprint={1911.05045},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
   }
```


