nflows
benchmark_VAE
nflows | benchmark_VAE | |
---|---|---|
2 | 4 | |
805 | 1,691 | |
1.5% | - | |
3.2 | 6.1 | |
6 months ago | 29 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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
-
[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).
benchmark_VAE
-
Researchers From INRIA France Propose ‘Pythae’: An Open-Source Python Library Unifying Common And State-of-the-Art Generative AutoEncoder (GAE) Implementations
Continue reading | Checkout the paper, github
-
[P] Pythae - Unifying generative autoencoder implementations in Python
Code for https://arxiv.org/abs/2206.08309 found: https://github.com/clementchadebec/benchmark_VAE
-
[P] Python library for Variational Autoencoder benchmarking
Github link: https://github.com/clementchadebec/benchmark_VAE
- Python library for Variational Autoencoder Benchmarking
What are some alternatives?
awesome-normalizing-flows - Awesome resources on normalizing flows.
Awesome-VAEs - A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
zuko - Normalizing flows in PyTorch
PyTorch-VAE - A Collection of Variational Autoencoders (VAE) in PyTorch.
cflow-ad - Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows"
scvi-tools - Deep probabilistic analysis of single-cell and spatial omics data
FrEIA - Framework for Easily Invertible Architectures
fastero - Python timeit CLI for the 21st century! colored output, multi-line input with syntax highlighting and autocompletion and much more!
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.
disentangling-vae - Experiments for understanding disentanglement in VAE latent representations
cloud_benchmarker - Cloud Benchmarker automates performance testing of cloud instances, offering insightful charts and tracking over time.
minimal_VAE_on_Mario - A minimal VAE trained on Super Mario Bros levels.