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
When I calculate uncertainty on the data points ( cifar-10 ), all the values I get are negative. So, it means the predicted loss for the data points are negative. How does it makes sense if the actual target loss is always positive?
When I calculate uncertainty on the data points ( cifar-10 ), all the values I get are negative. So, it means the predicted loss for the data points are negative. How does it makes sense if the actual target loss is always positive?