tfp.substrates.jax.random.spherical_uniform

Generates Tensor drawn from a uniform distribution on the sphere.

Main aliases

tfp.experimental.substrates.jax.random.spherical_uniform

tfp.substrates.jax.random.spherical_uniform(
    shape, dimension, dtype=tf.float32, seed=None, name=None
)

Args
`shape`	Vector-shaped, `int` `Tensor` representing shape of output.
`dimension`	Scalar `int` `Tensor`, representing the dimensionality of the space where the sphere is embedded.
`dtype`	(Optional) TF `dtype` representing `dtype` of output. Default value: `tf.float32`.
`seed`	PRNG seed; see `tfp.random.sanitize_seed` for details. Default value: `None` (i.e., no seed).
`name`	Python `str` name prefixed to Ops created by this function. Default value: `None` (i.e., 'random_spherical_uniform').

Returns
`spherical_uniform`	`Tensor` with specified `shape` and `dtype` consisting of real values drawn from a spherical uniform distribution.

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.

Args