tf.keras.initializers.TruncatedNormal

TensorFlow 1 version View source on GitHub

Initializer that generates a truncated normal distribution.

Inherits From: Initializer

Used in the notebooks

Used in the tutorials

Initializers allow you to pre-specify an initialization strategy, encoded in the Initializer object, without knowing the shape and dtype of the variable being initialized.

These values are similar to values from a tf.initializers.RandomNormal except that values more than two standard deviations from the mean are discarded and re-drawn. This is the recommended initializer for neural network weights and filters.

Examples:

def make_variables(k, initializer):
  return (tf.Variable(initializer(shape=[k], dtype=tf.float32)),
          tf.Variable(initializer(shape=[k, k], dtype=tf.float32)))
v1, v2 = make_variables(
    3, tf.initializers.TruncatedNormal(mean=1., stddev=2.))
v1
<tf.Variable ... shape=(3,) ... numpy=array([...], dtype=float32)>
v2
<tf.Variable ... shape=(3, 3) ... numpy=

make_variables(4, tf.initializers.RandomUniform(minval=-1., maxval=1.))
(<tf.Variable...shape=(4,) dtype=float32...>, <tf.Variable...shape=(4, 4) ...

mean a python scalar or a scalar tensor. Mean of the random values to generate.
stddev a python scalar or a scalar tensor. Standard deviation of the random values to generate.
seed A Python integer. Used to create random seeds. See tf.random.set_seed for behavior.

Methods

from_config

View source

Instantiates an initializer from a configuration dictionary.

Example:

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

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

Returns
An Initializer instance.

get_config

View source

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

Returns
A JSON-serializable Python dict.

__call__

View source

Returns a tensor object initialized as specified by the initializer.

Args
shape Shape of the tensor.
dtype Optional dtype of the tensor. Only floating point types are supported.

Raises
ValueError If the dtype is not floating point