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 thresh_warmup is True, since Classwise_acc is mostly zero for all labels in 1st few epochs/iterations, loss for most of unlabeled samples are not masked out. Do you think this could create wrong associations among data. I understand that supervised labeled samples also counter some of this problem but it may also destabilize the training. Any thoughts on this would help. Thanks in advance.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
TorchSSL/models/flexmatch/flexmatch_utils.py
Line 44 in cb27456
When thresh_warmup is True, since Classwise_acc is mostly zero for all labels in 1st few epochs/iterations, loss for most of unlabeled samples are not masked out. Do you think this could create wrong associations among data. I understand that supervised labeled samples also counter some of this problem but it may also destabilize the training. Any thoughts on this would help. Thanks in advance.
Beta Was this translation helpful? Give feedback.
All reactions