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
With the implementation of #185 allowing for gradient computation wrt. the parameters given an attribution with canonizers, the BatchNorms seem to be leaking attribution even with zero_params='bias' on ResNet18.
The text was updated successfully, but these errors were encountered:
With the implementation of #185 allowing for gradient computation wrt. the parameters given an attribution with canonizers, the BatchNorms seem to be leaking attribution even with
zero_params='bias'
on ResNet18.The text was updated successfully, but these errors were encountered: