Closed LeroyChou closed 2 years ago
Hi
Auh, I get it. But why the former is numerically unstable? could you please give me more details?
It's because of the relative precision of floating point numbers. Smaller numbers have higher absolute precision. E.g. with float32, machine epsilon is around 1e-7, and (1 - 1e-8) is rounded off to 1, but there's no problem representing 1e-8. When sigmoid(lgt) is close to 1, it is likely to round off to 1, and then log(1-1) = -inf, which we can't use for the score.
I see. And the example you gave is great, it opened my eyes to it. Thank you.
Hi, thank you again.
I'm comparing the pose score you proposed in paper and implemented in codes such that I encounter some questions.
neg_mask_log_prob
by inversingmask_lgts
before feeding it into the logsigmoid. why do you inversemask_lgts
? Does it actually mean anything?