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
{{ message }}
This repository has been archived by the owner on Aug 3, 2021. It is now read-only.
When encoder parameter "normalization" is set to None according documentation, training fails with the next error message: TypeError: conv_bn_res_bn_actv() missing 2 required positional arguments: 'bn_momentum' and 'bn_epsilon'
The question is why it is using conv_bn_res_bn_actv() function, while "normalization" is set to None?
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
When encoder parameter "normalization" is set to None according documentation, training fails with the next error message:
TypeError: conv_bn_res_bn_actv() missing 2 required positional arguments: 'bn_momentum' and 'bn_epsilon'
The question is why it is using
conv_bn_res_bn_actv()
function, while "normalization" is set to None?The text was updated successfully, but these errors were encountered: