torchflows and normalizing_flows
These are competitors offering overlapping implementations of normalizing flow algorithms, where the more established kamenbliznashki/normalizing_flows provides a broader set of architectures (BNAF, Glow, MAF, RealNVP, planar flows) while davidnabergoj/torchflows emphasizes ease of use and extensibility for similar density estimation tasks.
About torchflows
davidnabergoj/torchflows
Modern normalizing flows in Python. Simple to use and easily extensible.
This library helps machine learning researchers and practitioners train generative models and estimate data density using modern normalizing flows. You provide your dataset, and it outputs a model that can generate new, similar data points or calculate the likelihood of existing ones. It's designed for those working with advanced machine learning models who need flexible tools for generative tasks.
About normalizing_flows
kamenbliznashki/normalizing_flows
Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows
This project offers tools to model complex data distributions, useful for tasks like generating new images or understanding the underlying structure of datasets. It takes in existing data, such as images or numerical tables, and outputs models that can recreate similar data or allow for subtle modifications. Researchers and data scientists who work with generative models or need robust density estimation will find this valuable.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work