RegisterKL
tf.contrib.distributions.RegisterKL
tf.distributions.RegisterKL
Defined in tensorflow/python/ops/distributions/kullback_leibler.py
.
See the guide: Statistical Distributions (contrib) > Kullback-Leibler Divergence
Decorator to register a KL divergence implementation function.
Usage:
@distributions.RegisterKL(distributions.Normal, distributions.Normal) def _kl_normal_mvn(norm_a, norm_b): # Return KL(norm_a || norm_b)
__init__
__init__( dist_cls_a, dist_cls_b )
Initialize the KL registrar.
dist_cls_a
: the class of the first argument of the KL divergence.dist_cls_b
: the class of the second argument of the KL divergence.__call__
__call__(kl_fn)
Perform the KL registration.
kl_fn
: The function to use for the KL divergence.kl_fn
TypeError
: if kl_fn is not a callable.ValueError
: if a KL divergence function has already been registered for the given argument classes.
© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/distributions/RegisterKL