tf.keras.initializers.Zeros

Class Zeros

Inherits From: Initializer

Aliases:

  • Class tf.initializers.zeros
  • Class tf.keras.initializers.Zeros
  • Class tf.keras.initializers.zeros
  • Class tf.zeros_initializer

Defined in tensorflow/python/ops/init_ops.py.

Initializer that generates tensors initialized to 0.

__init__

__init__(dtype=tf.dtypes.float32)

Initialize self. See help(type(self)) for accurate signature.

Methods

tf.keras.initializers.Zeros.__call__

__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.

tf.keras.initializers.Zeros.from_config

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.

tf.keras.initializers.Zeros.get_config

get_config()

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

Returns:

A JSON-serializable Python dict.