Module: tfp.random  |  TensorFlow Probability (original) (raw)

Module: tfp.random

TensorFlow Probability random samplers/utilities.

Functions

rademacher(...): Generates Tensor consisting of -1 or +1, chosen uniformly at random.

rayleigh(...): Generates Tensor of positive reals drawn from a Rayleigh distributions.

sanitize_seed(...): Map various PRNG seed flavors to a seed Tensor.

spherical_uniform(...): Generates Tensor drawn from a uniform distribution on the sphere.

split_seed(...): Splits a seed into n derived seeds.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2023-11-21 UTC.