Skip to main content

PyTorch NN based trainable spectral linear layers

Project description

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.

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}
   }

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

spectralLayersPyTorch-0.989.tar.gz (6.1 kB view hashes)

Uploaded Source

Built Distribution

spectralLayersPyTorch-0.989-py3-none-any.whl (8.2 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page