Kymatio: Scattering Transforms in Python
Abstract
The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks, including PyTorch and TensorFlow/Keras. The transforms are implemented on both CPUs and GPUs, the latter offering a significant speedup over the former. The package also has a small memory footprint. Source code, documentation, and examples are available under a BSD license at https://www.kymat.io.
Cite
Text
Andreux et al. "Kymatio: Scattering Transforms in Python." Machine Learning Open Source Software, 2020.Markdown
[Andreux et al. "Kymatio: Scattering Transforms in Python." Machine Learning Open Source Software, 2020.](https://mlanthology.org/mloss/2020/andreux2020jmlr-kymatio/)BibTeX
@article{andreux2020jmlr-kymatio,
title = {{Kymatio: Scattering Transforms in Python}},
author = {Andreux, Mathieu and Angles, Tomás and Exarchakis, Georgios and Leonarduzzi, Roberto and Rochette, Gaspar and Thiry, Louis and Zarka, John and Mallat, Stéphane and Andén, Joakim and Belilovsky, Eugene and Bruna, Joan and Lostanlen, Vincent and Chaudhary, Muawiz and Hirn, Matthew J. and Oyallon, Edouard and Zhang, Sixin and Cella, Carmine and Eickenberg, Michael},
journal = {Machine Learning Open Source Software},
year = {2020},
pages = {1-6},
volume = {21},
url = {https://mlanthology.org/mloss/2020/andreux2020jmlr-kymatio/}
}