vmf_vae_nlp icon indicating copy to clipboard operation
vmf_vae_nlp copied to clipboard

Sampling from prior with kappa = 0

Open fermat97 opened this issue 5 years ago • 0 comments

Hi, I am not sure how you sample from the prior at test time. For the sampling from the prior, which is a vMF with kappa = 0, do you use vmf_batch.py? If I understood correctly it should not be dependent on mu while kappa = 0. According to the formulation of z = w*mu+v*(1-w^2)^(1/2), w must be zero, while I think it is not necessarily equal to zero in vmf_batch.py. Do you use another function?

fermat97 avatar Mar 19 '19 09:03 fermat97