Module: tf.random

TensorFlow 1 version

Public API for tf.random namespace.

Modules

experimental module: Public API for tf.random.experimental namespace.

Functions

all_candidate_sampler(...): Generate the set of all classes.

categorical(...): Draws samples from a categorical distribution.

fixed_unigram_candidate_sampler(...): Samples a set of classes using the provided (fixed) base distribution.

gamma(...): Draws shape samples from each of the given Gamma distribution(s).

learned_unigram_candidate_sampler(...): Samples a set of classes from a distribution learned during training.

log_uniform_candidate_sampler(...): Samples a set of classes using a log-uniform (Zipfian) base distribution.

normal(...): Outputs random values from a normal distribution.

poisson(...): Draws shape samples from each of the given Poisson distribution(s).

set_seed(...): Sets the graph-level random seed.

shuffle(...): Randomly shuffles a tensor along its first dimension.

stateless_categorical(...): Draws deterministic pseudorandom samples from a categorical distribution.

stateless_normal(...): Outputs deterministic pseudorandom values from a normal distribution.

stateless_truncated_normal(...): Outputs deterministic pseudorandom values, truncated normally distributed.

stateless_uniform(...): Outputs deterministic pseudorandom values from a uniform distribution.

truncated_normal(...): Outputs random values from a truncated normal distribution.

uniform(...): Outputs random values from a uniform distribution.

uniform_candidate_sampler(...): Samples a set of classes using a uniform base distribution.