nflows
Normalizing flows in PyTorch (by bayesiains)
cflow-ad
Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows" (by gudovskiy)
nflows | cflow-ad | |
---|---|---|
2 | 1 | |
805 | 222 | |
1.5% | - | |
3.2 | 4.3 | |
6 months ago | 9 months ago | |
Python | Python | |
MIT License | BSD 3-clause "New" or "Revised" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
nflows
Posts with mentions or reviews of nflows.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-02-07.
-
[P] Zuko, a fresh approach to normalizing flows in PyTorch
Normalizing flows (NFs) are very useful tools to build and train expressive parametric distributions. There exists a few libraries for NFs in PyTorch such as nflows, FrEIA and FlowTorch but, in my opinion, their complex APIs and the lack of documentation (except for FrEIA) makes them hard to approach. I initially planned on contributing to their repositories as they did not implement some architectures like neural autoregressive flow, unconstrained monotonic neural networks, sum-of-square polynomial flow or continuous normalizing flow. Unfortunately, none of the libraries seemed under active development anymore at the time.
-
[D] Normalizing flows for distributions with finit support
You can just start from a uniform distribution in [0,1]D and use a mapping with a finite domain/reach. One example would be a spline (see 1906.04032, or here https://github.com/bayesiains/nflows).
cflow-ad
Posts with mentions or reviews of cflow-ad.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Using GANs for defect generation
Thanks for the help.I am using the cflow-ad architecture.
What are some alternatives?
When comparing nflows and cflow-ad you can also consider the following projects:
awesome-normalizing-flows - Awesome resources on normalizing flows.
fcdd - Repository for the Explainable Deep One-Class Classification paper
zuko - Normalizing flows in PyTorch
pyod - A Comprehensive and Scalable Python Library for Outlier Detection (Anomaly Detection)
benchmark_VAE - Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
FrEIA - Framework for Easily Invertible Architectures
flowtorch - This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a community of users and contributors by focusing initially on complete infra and documentation for how to use and create components.