Initializes scale depending on output_min and output_max.
tfl.kronecker_factored_lattice_lib.scale_initializer(
units, num_terms, 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.
Args |
units
|
Output dimension of the layer. Each unit's scale will be initialized
identically.
|
num_terms
|
Number of independently trained submodels per unit, the outputs
of which are averaged to get the final output.
|
output_min
|
None or minimum layer output.
|
output_max
|
None or maximum layer output.
|
Returns |
Kronecker-Factored Lattice scale of shape: (units, num_terms) .
|