Closed Rzx520 closed 1 year ago
Hi @Rzx520, Notice there is a balance here between K_AP50 and U_R50. I chose the checkpoint I thought was best --although this is somewhat subjective.
You can select the model with the highest U_R, the them K_AP wouldn't be as high
Best, Orr
I understand. Thanks
It is indeed like this. We can see that the U_R50 has decreased even after the training time has increased. I am quite puzzled, so why not choose the model with the highest U_R50? @orrzohar