VariationalEvaluation¶

class tfsnippet.VariationalEvaluation(vi)¶

Bases: object

Factory for variational evaluation outputs.

Methods Summary

`importance_sampling_log_likelihood`([name])	Compute \(log p(x)\) by importance sampling.
`is_loglikelihood`([name])	Short-cut for `importance_sampling_log_likelihood()`.

Methods Documentation

importance_sampling_log_likelihood(name=None)¶

Compute \(log p(x)\) by importance sampling.

Parameters:	name (str) – TensorFlow name scope of the graph nodes. (default “importance_sampling_log_likelihood”)
Returns:	The per-data \(log p(x)\).
Return type:	tf.Tensor