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
RT.
Maybe with CUDA, LogME costs less time? Or if this is the problem setting assuming the transferability evaluation can not access GPU? (but the feature extraction part needs GPU?)
The text was updated successfully, but these errors were encountered:
Kyfafyd
changed the title
Why the LogME is implemented in torch but in numpy?
Why the LogME is implemented not in torch but in numpy?
Sep 13, 2022
RT.
Maybe with CUDA, LogME costs less time? Or if this is the problem setting assuming the transferability evaluation can not access GPU? (but the feature extraction part needs GPU?)
The text was updated successfully, but these errors were encountered: