tf.keras.initializers.get

Retrieves a Keras initializer object via an identifier.

The identifier may be the string name of a initializers function or class (case-sensitively).

identifier = 'Ones'
keras.initializers.deserialize(identifier)
<...keras.initializers.initializers.Ones...>

You can also specify config of the initializer to this function by passing dict containing class_name and config as an identifier. Also note that the class_name must map to a Initializer class.

cfg = {'class_name': 'Ones', 'config': {} }
keras.initializers.deserialize(cfg)
<...keras.initializers.initializers.Ones...>

In the case that the identifier is a class, this method will return a new instance of the class by its constructor.

identifier String or dict that contains the initializer name or configurations.

Initializer instance base on the input identifier.