I am trying to create a
DenseFlipout layer with a
GeneralizedNormal distribution for the kernel and Laplace distribution for the biases.
What should the
bias_posterior_fn in the arguments be?
I know in the
DenseVariational case, a function that takes in
kernel_size, bias_size, dtype would work. But now the
dtype, shape, name, trainable, add_variable_fn.
I do not know what to pass in for the
add_variable_fn and how this function works.
Any suggestions would be greatly appreciated.