Module: tfp.experimental

TensorFlow Probability API-unstable package.

This package contains potentially useful code which is under active development with the intention eventually migrate to TFP proper. All code in tfp.experimental should be of production quality, i.e., idiomatically consistent, well tested, and extensively documented. tfp.experimental code relaxes the TFP non-experimental contract in two regards:

  1. tfp.experimental has no API stability guarantee. The public footprint of tfp.experimental code may change without notice or warning.
  2. Code outside tfp.experimental cannot depend on code within tfp.experimental.

You are welcome to try any of this out (and tell us how well it works for you!).

Modules

auto_batching module: TensorFlow Probability auto-batching package.

bayesopt module: TensorFlow Probability experimental Bayesopt package.

bijectors module: TensorFlow Probability experimental bijectors package.

distribute module: Experimental module for doing distributed log prob calculations.

distributions module: TensorFlow Probability experimental distributions package.

joint_distribution_layers module: Experimental Joint Distribution Layers library.

linalg module: Experimental tools for linear algebra.

marginalize module: Marginalizable probability distributions.

math module: Experimental math.

mcmc module: TensorFlow Probability experimental MCMC package.

nn module: Tools for building neural networks.

parallel_filter module: TensorFlow Probability experimental parallel filtering package.

psd_kernels module: TensorFlow Probability experimental PSD kernels package.

sequential module: TensorFlow Probability experimental sequential estimation package.

stats module: Statistical functions.

sts_gibbs module: Gibbs sampling inference for structural time series models.

substrates module: TensorFlow Probability alternative substrates.

tangent_spaces module: TensorFlow Probability experimental tangent spaces package.

util module: TensorFlow Probability experimental python utilities.

vi module: Experimental methods and objectives for variational inference.

Classes

class AutoCompositeTensor: Recommended base class for @auto_composite_tensor-ified classes.

Functions

as_composite(...)

auto_composite_tensor(...): Automagically generate CompositeTensor behavior for cls.

register_composite(...)