Skip to Main content Skip to Navigation
Journal articles

Kymatio: Scattering Transforms in Python

Abstract : The wavelet scattering transform is an invariant 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. All transforms may be executed on a GPU (in addition to CPU), offering a considerable speed up over CPU implementations. The package also has a small memory footprint, resulting inefficient memory usage. The source code, documentation, and examples are available undera BSD license at https://www.kymat.io/
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02945354
Contributor : Edouard Oyallon <>
Submitted on : Tuesday, September 22, 2020 - 11:18:01 AM
Last modification on : Tuesday, October 6, 2020 - 11:06:17 AM

Links full text

Identifiers

  • HAL Id : hal-02945354, version 1
  • ARXIV : 1812.11214

Citation

Mathieu Andreux, Tomás Angles, Georgios Exarchakis, Roberto Leonarduzzi, Gaspar Rochette, et al.. Kymatio: Scattering Transforms in Python. Journal of Machine Learning Research, Microtome Publishing, 2020, 21 (60), pp.1-6. ⟨hal-02945354⟩

Share

Metrics

Record views

30