VariationalInference¶
-
class
tfsnippet.VariationalInference(log_joint, latent_log_probs, axis=None)¶ Bases:
objectClass for variational inference.
Attributes Summary
axisGet the axis or axes to be considered as the sampling dimensions of latent variables. evaluationGet the factory for evaluation outputs. latent_log_probGet the summed log-density of latent variables. latent_log_probsGet the log-densities of latent variables. log_jointGet the log-joint of the model. lower_boundGet the factory for variational lower-bounds. trainingGet the factory for training objectives. Attributes Documentation
-
axis¶ Get the axis or axes to be considered as the sampling dimensions of latent variables.
-
evaluation¶ Get the factory for evaluation outputs.
Returns: The factory for evaluation outputs. Return type: VariationalEvaluation
-
latent_log_prob¶ Get the summed log-density of latent variables.
Returns: The summed log-density of latent variables. Return type: tf.Tensor
-
latent_log_probs¶ Get the log-densities of latent variables.
Returns: The log-densities of latent variables. Return type: tuple[tf.Tensor]
-
log_joint¶ Get the log-joint of the model.
Returns: The log-joint of the model. Return type: tf.Tensor
-
lower_bound¶ Get the factory for variational lower-bounds.
Returns: The factory for variational lower-bounds. Return type: VariationalLowerBounds
-
training¶ Get the factory for training objectives.
Returns: The factory for training objectives. Return type: VariationalTrainingObjectives
-