tf.random.stateless_normal  |  TensorFlow v2.16.1 (original) (raw)

tf.random.stateless_normal

Stay organized with collections Save and categorize content based on your preferences.

Outputs deterministic pseudorandom values from a normal distribution.

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.random.stateless_normal

tf.random.stateless_normal(
    shape,
    seed,
    mean=0.0,
    stddev=1.0,
    dtype=tf.dtypes.float32,
    name=None,
    alg='auto_select'
)

Used in the notebooks

Used in the guide Used in the tutorials
Random number generation Random noise generation in TFF Multiple changepoint detection and Bayesian model selection TFP Release Notes notebook (0.11.0) Substantial Undocumented Infection Facilitates the Rapid Dissemination of Novel Coronavirus (SARS-CoV2)

This is a stateless version of tf.random.normal: if run twice with the same seeds and shapes, it will produce the same pseudorandom numbers. The output is consistent across multiple runs on the same hardware (and between CPU and GPU), but may change between versions of TensorFlow or on non-CPU/GPU hardware.

Args
shape A 1-D integer Tensor or Python array. The shape of the output tensor.
seed A shape [2] Tensor, the seed to the random number generator. Must have dtype int32 or int64. (When using XLA, only int32 is allowed.)
mean A 0-D Tensor or Python value of type dtype. The mean of the normal distribution.
stddev A 0-D Tensor or Python value of type dtype. The standard deviation of the normal distribution.
dtype The float type of the output: float16, bfloat16, float32,float64. Defaults to float32.
name A name for the operation (optional).
alg The RNG algorithm used to generate the random numbers. Seetf.random.stateless_uniform for a detailed explanation.
Returns
A tensor of the specified shape filled with random normal values.

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. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.