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
Are the training hyper-parameters same for OxUvA as well? 1 million iterations, with a batch size of 8? If not, what values do you use for 'epochs' (not iterations), 'lr' and 'bsize' in main_oxuva.py?
The text was updated successfully, but these errors were encountered:
Are the training hyper-parameters same for OxUvA as well? 1 million iterations, with a batch size of 8? If not, what values do you use for 'epochs' (not iterations), 'lr' and 'bsize' in main_oxuva.py?
The text was updated successfully, but these errors were encountered: