Wavelet scattering transforms in Python with GPU acceleration
Kymatio: Wavelet scattering in Python - v0.3.0 “Erdre”
Kymatio is an implementation of the wavelet scattering transform in the Python programming language, suitable for large-scale numerical experiments in signal processing and machine learning. Scattering transforms are translation-invariant signal representations implemented as convolutional networks whose filters are not learned, but fixed (as wavelet filters).
Use Kymatio if you need a library that:
- supports 1-D, 2-D, and 3-D wavelets,
- integrates wavelet scattering in a deep learning architecture, and
- runs seamlessly on CPU and GPU hardware, with major deep learning APIs, such as PyTorch, TensorFlow, and Jax.
The Kymatio environment
The Kymatio organization associates the developers of several pre-existing packages for wavelet scattering, including
Interfacing Kymatio into deep learning frameworks allows the programmer to backpropagate the gradient of wavelet scattering coefficients, thus integrating them within an end-to-end trainable pipeline, such as a deep neural network.
Each of these algorithms is written in a high-level imperative paradigm, making it portable to any Python library for array operations as long as it enables complex-valued linear algebra and a fast Fourier transform (FFT).
Each algorithm comes packaged with a frontend and backend. The frontend takes care of interfacing with the user. The backend defines functions necessary for computation of the scattering transform.
Currently, there are eight available frontend–backend pairs, NumPy (CPU), scikit-learn (CPU), pure PyTorch (CPU and GPU), PyTorch>=1.10 (CPU and GPU), PyTorch+scikit-cuda (GPU), PyTorch>=1.10+scikit-cuda (GPU), TensorFlow (CPU and GPU), Keras (CPU and GPU), and Jax (CPU and GPU).
Kymatio integrates the construction of wavelet filter banks in 1D, 2D, and 3D, as well as memory-efficient algorithms for extracting wavelet scattering coefficients, under a common application programming interface.
Running Kymatio on a graphics processing unit (GPU) rather than a multi-core conventional central processing unit (CPU) allows for significant speedups in computing the scattering transform. The current speedup with respect to CPU-based MATLAB code is of the order of 10 in 1D and 3D and of the order of 100 in 2D.
We refer to our official benchmarks for further details.
How to cite
If you use this package, please cite our paper Kymatio: Scattering Transforms in Python:
Andreux M., Angles T., Exarchakis G., Leonarduzzi R., Rochette G., Thiry L., Zarka J., Mallat S., Andén J., Belilovsky E., Bruna J., Lostanlen V., Chaudhary M., Hirn M. J., Oyallon E., Zhang S., Cella C., Eickenberg M. (2020). Kymatio: Scattering Transforms in Python. Journal of Machine Learning Research 21(60):1−6, 2020. (paper) (bibtex)
- Python (>= 3.7)
- SciPy (>= 0.13)
We strongly recommend running Kymatio in an Anaconda environment, because this simplifies the installation of other
dependencies. You may install the latest version of Kymatio using the package manager
pip, which will automatically download
Kymatio from the Python Package Index (PyPI):
pip install kymatio
Linux and macOS are the two officially supported operating systems.
To explicitly call the NumPy frontend, run:
from kymatio.numpy import Scattering2D scattering = Scattering2D(J=2, shape=(32, 32))
You can call also call
Scattering2D as a scikit-learn
from kymatio.sklearn import Scattering2D scattering_transformer = Scattering2D(2, (32, 32))
Using PyTorch, you can instantiate
Scattering2D as a
from kymatio.torch import Scattering2D scattering = Scattering2D(J=2, shape=(32, 32))
TensorFlow and Keras
Similarly, in TensorFlow, you can instantiate
Scattering2D as a
from kymatio.tensorflow import Scattering2D scattering = Scattering2D(J=2, shape=(32, 32))
Alternatively, you can call
Scattering2D as a Keras
from tensorflow.keras.layers import Input from kymatio.keras import Scattering2D inputs = Input(shape=(32, 32)) scattering = Scattering2D(J=2)(inputs)
Finally, with Jax installed, you can also instantiate a Jax
from kymatio.jax import Scattering2D scattering = Scattering2D(J=2, shape=(32, 32))
Installation from source
Assuming the Kymatio source has been downloaded, you may install it by running
pip install -r requirements.txt python setup.py install
Developers can also install Kymatio via:
pip install -r requirements.txt python setup.py develop
sklearn, only allow processing on the CPU and are therefore slower. The
jax frontends, however, also support GPU processing, which can significantly accelerate computations. Additionally, the
torch backend supports an optimized
skcuda backend which currently provides the fastest performance in computing scattering transforms.
To use it, you must first install the
pip install scikit-cuda cupy
Then you may instantiate a scattering object using the
from kymatio.torch import Scattering2D scattering = Scattering2D(J=2, shape=(32, 32), backend='torch_skcuda')
The documentation of Kymatio is officially hosted on the kymat.io website.
Building the documentation from source
The documentation can also be found in the
doc/ subfolder of the GitHub repository.
To build the documentation locally, please clone this repository and run
pip install -r requirements_optional.txt cd doc; make clean; make html
We wish to thank the Scientific Computing Core at the Flatiron Institute for the use of their computing resources for testing.
We would also like to thank École Normale Supérieure for their support.
Kyma (κύμα) means wave in Greek. By the same token, Kymatio (κυμάτιο) means wavelet.
Note that the organization and the library are capitalized (Kymatio) whereas the corresponding Python module is written in lowercase (
The recommended pronunciation for Kymatio is kim-ah-tio. In other words, it rhymes with patio, not with ratio.
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.