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
Thanks for pointing this out! The reference to the checkpoint for mixed-4 was not correct and has been updated on the last commit. The correct checkpoint is checkpoint_0799.pth.tar instead of checkpoint_0199.pth.tar for this dataset, as we use 1.3M * 4 samples, but an epoch is still the same number of update iterations as when training with just 1.3M samples.
Hi, I get this error when I run
./scripts/download_pretrained_models/download_large_scale_encoders.sh
:The text was updated successfully, but these errors were encountered: