Hi, in your new code, there is no implementation about the local reparameterization trick. If I want to use it to compute the output of the convolution layer, I should replace sigma^2 with alpha mu^2 (just like the implementation in your old code). But should I also replace sigma^2 with alpha mu^2 when computing the KL divergence? i.e. should KL also be affected by the parameter alpha? Why or why not? Thanks!
Hi, in your new code, there is no implementation about the local reparameterization trick. If I want to use it to compute the output of the convolution layer, I should replace sigma^2 with alpha mu^2 (just like the implementation in your old code). But should I also replace sigma^2 with alpha mu^2 when computing the KL divergence? i.e. should KL also be affected by the parameter alpha? Why or why not? Thanks!