Open shifdz opened 2 years ago
I've been wondering about the easiest way to implement this too. Have you made any progress? It seems like tfd.JointDistributionSequential should work but it seems like all the tfp.layers don't accept tfd.JointDistributionSequential.
The default prior in
Convolution3DReparametrization()
istfp.layers.default_multivariate_normal_fn
which is an isotrophic Gaussian with mean 0 and standard devitaion1. The posterior istfp_layers_util.default_mean_field_normal_fn()
. Is it possible to specify a hierarchical model for prior and posterior for example,prior~N(0,sigma)
andsigma~Gamma(a1,b1)
? How can I implement this in Tensorflow probability, may be withtfd.JointDistributionSequential
?