Module: tfp.layers.util
Stay organized with collections
Save and categorize content based on your preferences.
Utilities for probabilistic layers.
Functions
default_loc_scale_fn(...)
: Makes closure which creates loc
, scale
params from tf.get_variable
.
default_mean_field_normal_fn(...)
: Creates a function to build Normal distributions with trainable params.
default_multivariate_normal_fn(...)
: Creates multivariate standard Normal
distribution.
deserialize_function(...)
: Deserializes the Keras-serialized function.
serialize_function(...)
: Serializes function for Keras.
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 2023-11-21 UTC.
[null,null,["Last updated 2023-11-21 UTC."],[],[],null,["# Module: tfp.layers.util\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/probability/blob/v0.23.0/tensorflow_probability/python/layers/util.py) |\n\nUtilities for probabilistic layers.\n\nFunctions\n---------\n\n[`default_loc_scale_fn(...)`](../../tfp/layers/default_loc_scale_fn): Makes closure which creates `loc`, `scale` params from `tf.get_variable`.\n\n[`default_mean_field_normal_fn(...)`](../../tfp/layers/default_mean_field_normal_fn): Creates a function to build Normal distributions with trainable params.\n\n[`default_multivariate_normal_fn(...)`](../../tfp/layers/default_multivariate_normal_fn): Creates multivariate standard `Normal` distribution.\n\n[`deserialize_function(...)`](../../tfp/layers/util/deserialize_function): Deserializes the Keras-serialized function.\n\n[`serialize_function(...)`](../../tfp/layers/util/serialize_function): Serializes function for Keras."]]