SiCheng Li
SiCheng Li
I met the same issue too
> I got the result too. But xiaoyu li didn't provide the fitting code (as mentioned in the paper), so the result is not good as shown in the paper.
Thanks a lot!. By the way, could you please clarify what range of loss values is typically expected for DINOv3 training? In other words, around what loss level would you...
@alexisdrakopoulos Yes, but there still have some bugs and I'm trying to fix, maybe be we can discuss furthur about how to make this work (DM me with email or...