search

htjb / margarine

Code to replicate posterior probability distributions with bijectors/KDEs and perform marginal KL/bayesian dimensionality calculations.
MIT License
13 stars 8 forks source link

Runtime #20

Closed htjb closed 1 year ago

htjb commented 1 year ago

Curious whether the code can be sped up by using the tf.function tool provided in tensorflow to wrap the train_step function in maf.py. tf.function converts functions in to graphs rather than executing them using eager execution.

htjb commented 1 year ago

Resolved in #32.