Oryx
A library for probabilistic reasoning and statistical analysis integrated with TensorFlow and JAX.
What is Oryx?
TensorFlow Probability is a library for probabilistic reasoning and statistical analysis built for the TensorFlow ecosystem. It provides tools for integrating probabilistic methods with deep learning, enabling gradient-based inference, scalable computation on large datasets, and Bayesian modeling. It also functions as "Tensor-friendly Probability" in pure JAX, offering flexibility across different machine learning frameworks.
Data scientists, machine learning researchers, and developers working on probabilistic models, Bayesian inference, or statistical analysis within TensorFlow or JAX-based projects.
Developers choose TensorFlow Probability for its deep integration with TensorFlow and JAX, enabling scalable probabilistic modeling with hardware acceleration. Its layered architecture provides everything from statistical building blocks to advanced inference algorithms, making it a comprehensive solution for probabilistic machine learning.
Overview
Probabilistic reasoning and statistical analysis in TensorFlow
Use Cases
Best For
- Building Bayesian neural networks with uncertainty quantification
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
