tf.keras.backend.random_normal_variable

TensorFlow 1 version View source on GitHub

Instantiates a variable with values drawn from a normal distribution.

tf.keras.backend.random_normal_variable(
    shape, mean, scale, dtype=None, name=None, seed=None
)

shape Tuple of integers, shape of returned Keras variable.
mean Float, mean of the normal distribution.
scale Float, standard deviation of the normal distribution.
dtype String, dtype of returned Keras variable.
name String, name of returned Keras variable.
seed Integer, random seed.

A Keras variable, filled with drawn samples.

Example:

kvar = tf.keras.backend.random_normal_variable((2,3), 0, 1)
kvar
<tf.Variable 'Variable:0' shape=(2, 3) dtype=float32, numpy=...,
dtype=float32)>