Uni-Summer

Yeah, I just fixed it. Made a stupid mistake. And the separate value in epoch 5 is, L_ice: 0.1275, L_KL: 0.0007, L_dice: 0.3636. It seems like the KL value is...

There is no balance factor, just the pure L_KL value. Could you bother to tell the suggested value range of L_KL at the training beginning? Thanks!

hey, sorry to bother, but have you solved this error? I just met the same problem. It would help a lot if you could reply. Thanks so much. Best. Ziying

Thanks so much for your reply! If I may ask, have you tried any other skull-stripping algorithms to perform well on CT? As a newbie, your advice can really help...

yes, I also tried FSL BET, and it performs badly in my case. however, this code only suits part of my dataset, it went wrong with some data. And the...