Kymatio: Scattering Transforms in Python

by   Mathieu Andreux, et al.

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


page 1

page 2

page 3

page 4


Geometric Scattering on Manifolds

We present a mathematical model for geometric deep learning based upon a...

Quantum Energy Regression using Scattering Transforms

We present a novel approach to the regression of quantum mechanical ener...

PeriPy – A High Performance OpenCL Peridynamics Package

This paper presents a lightweight, open-source and high-performance pyth...

Triangulating Python Performance Issues with Scalene

This paper proposes Scalene, a profiler specialized for Python. Scalene ...

PySDM v1: particle-based cloud modelling package for warm-rain microphysics and aqueous chemistry

PySDM is an open-source Python package for simulating the dynamics of pa...

Essential Scattering Applications for Everyone. Overview

ESCAPE is a free python package and framework for creating applications ...

PyLightcurve-torch: a transit modelling package for deep learning applications in PyTorch

We present a new open source python package, based on PyLightcurve and P...

Code Repositories


Wavelet scattering transforms in Python with GPU acceleration

view repo

Please sign up or login with your details

Forgot password? Click here to reset