Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf.compat.v1.keras.initializers.glorot_normal

View source on GitHub

The Glorot normal initializer, also called Xavier normal initializer.

Inherits From: VarianceScaling

tf.compat.v1.keras.initializers.glorot_normal(
    seed=None, dtype=tf.dtypes.float32
)

It draws samples from a truncated normal distribution centered on 0 with standard deviation (after truncation) given by stddev = sqrt(2 / (fan_in + fan_out)) where fan_in is the number of input units in the weight tensor and fan_out is the number of output units in the weight tensor.

Args:

  • seed: A Python integer. Used to create random seeds. See tf.compat.v1.set_random_seed for behavior.
  • dtype: Default data type, used if no dtype argument is provided when calling the initializer. Only floating point types are supported.

References:

Glorot et al., 2010 (pdf)

Methods

__call__

View source

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

Returns a tensor object initialized as specified by the initializer.

Args:

  • shape: Shape of the tensor.
  • dtype: Optional dtype of the tensor. If not provided use the initializer dtype.
  • partition_info: Optional information about the possible partitioning of a tensor.

from_config

View source

@classmethod
from_config(
    cls, config
)

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

get_config()

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

Returns:

A JSON-serializable Python dict.