You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is it more reasonable to use abs(softmax(logit) - 0.5) ?
It seems that Figure2(c) use something like the latter equation to calc (un)certainty map.
Thanks.
The text was updated successfully, but these errors were encountered:
lisosia
changed the title
Question about model uncertainty of non-bayesian model when training
Question about calculating uncertainty of non-bayesian model when training
Aug 27, 2020
Is it more reasonable to use abs(softmax(logit) - 0.5) ?
It seems that Figure2(c) use something like the latter equation to calc (un)certainty map.
Thanks.
Hi, my code doesn't calculate uncertainty map for non-bayesian model. The comment before that four lines of code is mistakenly written (sorry).
The Figure 2(c) in the paper was indeed visualized based on uncertainty = 1 - abs(softmax(logit) - 0.5)*2 for demonstration.
Hi, Thank you for your great work.
When training for non-bayesian model,
it seems that certainty map is calculated by
softmax(logit)
:UMA/train_bayesian_adapt.py
Lines 359 to 362 in b72dad9
Is it more reasonable to use
abs(softmax(logit) - 0.5)
?It seems that Figure2(c) use something like the latter equation to calc (un)certainty map.
Thanks.
The text was updated successfully, but these errors were encountered: