gradientinstitute / aboleth

A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation
Apache License 2.0
127 stars 10 forks source link

Feature/#173 #175

Closed dsteinberg closed 6 years ago

dsteinberg commented 6 years ago

This makes all tf.Variables in the code also get a summary histogram, it also removes the optimisation of the prior standard deviation (and allows the user to explicitly optimise it if they choose, like length scales etc).