tf.raw_ops.StatelessTruncatedNormalV2 | TensorFlow v2.16.1 (original) (raw)

tf.raw_ops.StatelessTruncatedNormalV2

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

Outputs deterministic pseudorandom values from a truncated normal distribution.

View aliases

Compat aliases for migration

tf.compat.v1.raw_ops.StatelessTruncatedNormalV2

tf.raw_ops.StatelessTruncatedNormalV2(
    shape,
    key,
    counter,
    alg,
    dtype=tf.dtypes.float32,
    name=None
)

The generated values follow a normal distribution with mean 0 and standard deviation 1, except that values whose magnitude is more than 2 standard deviations from the mean are dropped and re-picked.

The outputs are a deterministic function of shape, key, counter and alg.

Args
shape	A Tensor. Must be one of the following types: int32, int64. The shape of the output tensor.
key	A Tensor of type uint64. Key for the counter-based RNG algorithm (shape uint64[1]).
counter	A Tensor of type uint64. Initial counter for the counter-based RNG algorithm (shape uint64[2] or uint64[1] depending on the algorithm). If a larger vector is given, only the needed portion on the left (i.e. [:N]) will be used.
alg	A Tensor of type int32. The RNG algorithm (shape int32[]).
dtype	An optional tf.DType from: tf.half, tf.bfloat16, tf.float32, tf.float64. Defaults to tf.float32. The type of the output.
name	A name for the operation (optional).

Returns
A Tensor of type dtype.

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.