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
This can be fixed by calculating the mean or max of all atoms and directions. With that we have one metric per structure. What do you think is better? Here I have plotted the two options as an example. The upper two pictures show the mean(uncertainty) (left) max(uncertainty) (right) plotted as an error of the max(rev_force) against the configiration. The lower pictures show the mean(uncertainty) (left) and max(uncertainty) (right) plotted against the configiration.
ThresholdSelection currently can only be used with energies.
The text was updated successfully, but these errors were encountered: