nflows is a comprehensive collection of normalizing flows using PyTorch.
To install from PyPI:
python -m pip install nflows
To install and add nflows to a project with pixi, from the project directory run
pixi add nflows
and to install into a particular conda environment with conda, in the activated environment run
conda install --channel conda-forge nflows
To define a flow:
from nflows import transforms, distributions, flows
# Define an invertible transformation.
transform = transforms.CompositeTransform([
transforms.MaskedAffineAutoregressiveTransform(features=2, hidden_features=4),
transforms.RandomPermutation(features=2)
])
# Define a base distribution.
base_distribution = distributions.StandardNormal(shape=[2])
# Combine into a flow.
flow = flows.Flow(transform=transform, distribution=base_distribution)To evaluate log probabilities of inputs:
log_prob = flow.log_prob(inputs)To sample from the flow:
samples = flow.sample(num_samples)Additional examples of the workflow are provided in examples folder.
To install all the dependencies for development:
pip install -r requirements.txt
To cite the package:
@software{nflows,
author = {Conor Durkan and
Artur Bekasov and
Iain Murray and
George Papamakarios},
title = {{nflows}: normalizing flows in {PyTorch}},
month = nov,
year = 2020,
publisher = {Zenodo},
version = {v0.14},
doi = {10.5281/zenodo.4296287},
url = {https://doi.org/10.5281/zenodo.4296287}
}The version number is intended to be the one from nflows/version.py. The year/month correspond to the date of the release. BibTeX entries for other versions could be found on Zenodo.
If you're using spline-based flows in particular, consider citing the Neural Spline Flows paper: [bibtex].
nflows is derived from bayesiains/nsf originally published with
C. Durkan, A. Bekasov, I. Murray, G. Papamakarios, Neural Spline Flows, NeurIPS 2019. [arXiv] [bibtex]
nflows has been used in
Conor Durkan, Iain Murray, George Papamakarios, On Contrastive Learning for Likelihood-free Inference, ICML 2020. [arXiv].
Artur Bekasov, Iain Murray, Ordering Dimensions with Nested Dropout Normalizing Flows. [arXiv].
Tim Dockhorn, James A. Ritchie, Yaoliang Yu, Iain Murray, Density Deconvolution with Normalizing Flows. [arXiv].
nflows is used by the conditional density estimation package pyknos, and in turn the likelihood-free inference framework sbi.
