#167167th of 206 in ML frameworks and libraries
probability
Probabilistic modeling and Bayesian inference library for TensorFlow and JAX
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.4k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Nov 2024
- Language
- Jupyter Notebook
Missed the latest GitHub check; these facts may be older.
Overview
TensorFlow Probability provides probability distributions, bijectors, joint distribution models and probabilistic neural network layers, plus inference through MCMC (including Hamiltonian Monte Carlo), variational inference and stochastic optimizers. It runs on TensorFlow, and a JAX substrate is available via tensorflow_probability.substrates.jax. Examples are mostly Jupyter notebooks covering hierarchical models, Bayesian neural networks and mixture models.
Who it is for: Researchers and engineers doing Bayesian modeling and probabilistic ML in Python
Strengths
- Covers distributions, bijectors, MCMC and variational inference in one library
- Runs on TensorFlow or pure JAX through a substrates import
- Batch and broadcasting semantics on distributions allow GPU-accelerated vectorized computation
- Many tutorial notebooks, including Eight Schools and Bayesian mixture models
Weaknesses
- README warns interfaces may change at any time
- TensorFlow is not a pip dependency; it must be installed separately
- Last tagged release is 2024-11-08, well behind recent commits
- Building from source needs Bazel, and only up to 6.4.0 is supported
What it needs
- GPU optional
- Needs TensorFlow or tensorflow-cpu, JAX (optional substrate), Bazel 6.4.0 (source builds only)
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |