Constraints for tfl.layers.KroneckerFactoredLattice
scale.
tfl.kronecker_factored_lattice_layer.ScaleConstraints(
output_min=None, output_max=None
)
Constraints the scale variable to be between
[output_min-output_max, output_max-output_min]
such that the final output
of the layer is within the desired [output_min, output_max]
range, assuming
bias is properly fixed to be output_min
.
Args |
output_min
|
Same meaning as corresponding parameter of
KroneckerFactoredLattice .
|
output_max
|
Same meaning as corresponding parameter of
KroneckerFactoredLattice .
|
Methods
from_config
@classmethod
from_config(
config
)
Instantiates a weight constraint from a configuration dictionary.
Example:
constraint = UnitNorm()
config = constraint.get_config()
constraint = UnitNorm.from_config(config)
Args |
config
|
A Python dictionary, the output of get_config .
|
get_config
View source
get_config()
Standard Keras config for serialization.
__call__
View source
__call__(
scale
)
Applies constraints to scale
.
Args |
scale
|
Kronecker-Factored Lattice scale tensor of shape: (units,
num_terms) .
|
Returns |
Constrained and clipped scale.
|