Release notes
This is the 0.24.0 release of TensorFlow Probability. It is tested and stable against TensorFlow 2.16.1 and JAX 0.4.25 .
NOTE: In TensorFlow 2.16+, `tf.keras` (and `tf.initializers`, `tf.losses`, and `tf.optimizers`) refers to Keras 3. TensorFlow Probability is not compatible with Keras 3 -- instead TFP is continuing to use Keras 2, which is now packaged as `tf-keras` and `tf-keras-nightly` and is imported as `tf_keras`. When using TensorFlow Probability with TensorFlow, you must explicitly install Keras 2 along with TensorFlow (or install `tensorflow-probability[tf]` or `tfp-nightly[tf]` to automatically install these dependencies.)
Change notes
- TensorFlow Probability now supports Python 3.12.
* But note that many parts of `tfp.layers` and `tfp.experimental.nn` will raise errors because of a TensorFlow + wrapt bug (see https://github.com/tensorflow/tensorflow/issues/60687 ), which can be worked around by setting the environment variable `WRAPT_DISABLE_EXTENSIONS=true`.
- Added an experimental implementation of Chopin, Jacob, Papaspiliopoulos, "SMC^2: an efficient algorithm for sequential analysis of state-space models", Journal of the Royal Statistical Society Series B: Statistical Methodology 75.3 (2013). See https://github.com/tensorflow/probability/blob/v0.24.0/tensorflow_probability/python/experimental/mcmc/particle_filter.py#L766 .
- Added `tfp.experimental.fastgp`, a library for approximately training and evaluating Gaussian Processes in sub-O(n^3) time.
See https://github.com/tensorflow/probability/tree/r0.24/tensorflow_probability/python/experimental/fastgp .
Huge thanks to all the contributors to this release!
- Alessandro Slamitz
- Christopher Suter
- Colin Carroll
- Emily Fertig
- Gareth Williams
- Jacob Burnim
- Jake VanderPlas
- Matthew Feickert
- Pavel Sountsov
- Richard Levasseur
- Srinivas Vasudevan
- Thomas Colthurst
- Urs Köster