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
To resume training I tried to load a saved model from checkpoint, but it ran into the issue where the expected state_dict had module as a prefix to the keys as compared to the saved state_dict.
To resume training I tried to load a saved model from checkpoint, but it ran into the issue where the expected
state_dict
hadmodule
as a prefix to the keys as compared to the savedstate_dict
.This is similar to the following issue: pytorch forum, github issue.
I modified the loading code in the following way by adding
strict=False
for now:The text was updated successfully, but these errors were encountered: