I was looking at the TruncNormalDistcode and was wondering why were the samples re-clipped ('re' because they are already in [-1, 1] because of tfd.TruncatedNormal's sampling).
In practice it seems to me that this wouldn't create an issue as it is only re-clipped by 1e-6, but I am curious if I'm missing something.
Hi,
I was looking at the
TruncNormalDist
code and was wondering why were the samples re-clipped ('re' because they are already in[-1, 1]
because oftfd.TruncatedNormal
's sampling). In practice it seems to me that this wouldn't create an issue as it is only re-clipped by1e-6
, but I am curious if I'm missing something.Thanks!