tfl.kronecker_factored_lattice_lib.bias_initializer
Initializes bias depending on output_min and output_max.
tfl.kronecker_factored_lattice_lib.bias_initializer(
units, output_min, output_max, dtype=tf.float32
)
If both output_min and output_max are set, bias is initialized to their
average. If only output_min is set, bias is initialized to output_min. If only
output_max is set, bias is initialized to output_max. Otherwise bias is
initialized to zeros.
Args |
units
|
Output dimension of the layer. Each of units bias will be initialized
identically.
|
output_min
|
None or minimum layer output.
|
output_max
|
None or maximum layer output.
|
dtype
|
dtype
|
Returns |
Kronecker-Factored Lattice bias of shape: (units) .
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-08-02 UTC.
[null,null,["Last updated 2024-08-02 UTC."],[],[]]