nflows is a comprehensive collection of normalizing flows using PyTorch.
To install from PyPI:
pip install 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.
You can install all the dependencies using the environment.yml file to create a conda environment:
conda env create -f environment.yml
Alternatively, you can install via setup.py (the dev flag installs development and testing dependencies):
pip install -e ".[dev]"
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.