tfl.kronecker_factored_lattice_layer.ScaleInitializer

Initializes scale depending on output_min and output_max.

tfl.kronecker_factored_lattice_layer.ScaleInitializer(
    output_min, output_max
)

If both output_min and output_max are set, scale is initialized to half their difference, alternating signs for each term. If only output_min is set, scale is initialized to 1 for each term. If only output_max is set, scale is initialized to -1 for each term. Otherwise scale is initialized to alternate between 1 and -1 for each term.

output_min None or minimum layer output.
output_max None or maximum layer output.

Methods

from_config

@classmethod
from_config(
    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, the output of get_config.

Returns
A tf.keras.initializers.Initializer instance.

get_config

View source

get_config()

Standard Keras config for serializaion.

__call__

View source

__call__(
    shape, dtype=None, **kwargs
)

Returns weights of tfl.layers.KroneckerFactoredLattice scale.

Args
shape Must be: (units, num_terms).
dtype Standard Keras initializer param.
**kwargs Other args passed to tf.keras.initializers.Initializer call method.