tensorflow-probability has 1.2M monthly downloads and 4K GitHub stars. Version 0.25.0 supports Python 3.9+, first published in 2018.
It is stably maintained under a permissive license, last released in Nov 2024.
It is built on top of absl-py, cloudpickle and decorator. It is used by 204 tracked packages, including zfit, dopamine-rl and fastestimator-nightly.
GitHub topics include tensorflow, bayesian-methods and deep-learning.
Package Insights
- No releases in 549 days despite active commits
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100Weekly Downloads
GitHub Stars
Downloads by OS
Python Versions
Top Countries
Dependencies
5 optional dependencies
- jax[jax]
- jaxlib[jax]
- tensorflow[tf]
- tensorflow-datasets[tfds]
- tf-keras[tf]
Used By
- zfit
- dopamine-rl
- fastestimator-nightly
- tfcausalimpact
- tensorflow-privacy
- lingvo
- probabilistic-word-embeddings
- tensor2tensor
- tff-nightly
- tf-agents
- tensorflow-gan
- ydata-synthetic
- gpflux
- tfp-causalimpact
- glmhmmt
- thetaflow
- waymo-open-dataset-tf-2-12-0
- trieste
- masa-safe-rl
- bark-ml
- magenta
- antspyt1w
- icenet
- gps-building-blocks
- peptcrnet
- tensorflow-compression
- pyrddlgym-jax
- qdax
- waymo-open-dataset-tf-2-11-0
- oryx
- mhcbooster
- phasespace
- bayeux-ml
- bpnet
- cleverhans
- scdef
- sgptools
- nobrainer
- pyvitae
- tensorflow-mri
- imspy
- example2410
- best-inference
- deepof
- angorapy
- tf-gnns
- alectio-sdk
- nabqr
- curriculumagent
- choice-learn