tf.compat.v1.random_normal_initializer

Initializer that generates tensors with a normal distribution.

tf.compat.v1.random_normal_initializer(
    mean=0.0,
    stddev=1.0,
    seed=None,
    dtype=tf.dtypes.float32
)

Migrate to TF2

Although it is a legacy compat.v1 API, this symbol is compatible with eager execution and tf.function.

To switch to TF2, switch to using either tf.initializers.RandomNormal or tf.keras.initializers.RandomNormal (neither from compat.v1) and pass the dtype when calling the initializer. Keep in mind that the default stddev and the behavior of fixed seeds have changed.

Structural Mapping to TF2

Before:

initializer = tf.compat.v1.random_normal_initializer(
  mean=mean,
  stddev=stddev,
  seed=seed,
  dtype=dtype)

weight_one = tf.Variable(initializer(shape_one))
weight_two = tf.Variable(initializer(shape_two))

After:

initializer = tf.initializers.RandomNormal(
  mean=mean,
  seed=seed,
  stddev=stddev)

weight_one = tf.Variable(initializer(shape_one, dtype=dtype))
weight_two = tf.Variable(initializer(shape_two, dtype=dtype))

How to Map Arguments

TF1 Arg NameTF2 Arg NameNote
meanmeanNo change to defaults
stddevstddevDefault changes from 1.0 to 0.05
seedseed
dtypedtypeThe TF2 native api only takes it as a __call__ arg, not a constructor arg.
partition_info-(__call__ arg in TF1) Not supported.

Description

meana python scalar or a scalar tensor. Mean of the random values to generate.
stddeva python scalar or a scalar tensor. Standard deviation of the random values to generate.
seedA Python integer. Used to create random seeds. See tf.compat.v1.set_random_seed for behavior.
dtypeDefault data type, used if no dtype argument is provided when calling the initializer. Only floating point types are supported.

Methods

from_config

View source

@classmethod
from_config(
    config
)

Instantiates an initializer from a configuration dictionary.

Example:

initializer = RandomUniform(-1, 1)
config = initializer.get_config()
initializer = RandomUniform.from_config(config)

Args
configA Python dictionary. It will typically be the output of get_config.

Returns
An Initializer instance.

get_config

View source

get_config()

Returns the configuration of the initializer as a JSON-serializable dict.

Returns
A JSON-serializable Python dict.

__call__

View source

__call__(
    shape, dtype=None, partition_info=None
)

Returns a tensor object initialized as specified by the initializer.

Args
shapeShape of the tensor.
dtypeOptional dtype of the tensor. If not provided use the initializer dtype.
partition_infoOptional information about the possible partitioning of a tensor.