tfmri.initializers.LecunUniform

class LecunUniform(seed=None)[source]

Bases: keras.initializers.initializers_v2.LecunUniform

Lecun uniform initializer.

Note

This initializer can be used as a drop-in replacement for tf.keras.initializers.LecunUniform. However, this one also supports initialization of complex-valued weights. Simply pass dtype='complex64' or dtype='complex128' to its __call__ method.

Also available via the shortcut function

tf.keras.initializers.lecun_uniform.

Draws samples from a uniform distribution within [-limit, limit], where limit = sqrt(3 / fan_in) (fan_in is the number of input units in the weight tensor).

Examples:

>>> # Standalone usage:
>>> initializer = tf.keras.initializers.LecunUniform()
>>> values = initializer(shape=(2, 2))

>>> # Usage in a Keras layer:
>>> initializer = tf.keras.initializers.LecunUniform()
>>> layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)
Args:
seed: A Python integer. Used to make the behavior of the initializer

deterministic. Note that a seeded initializer will not produce the same random values across multiple calls, but multiple initializers will produce the same sequence when constructed with the same seed value.

References: