Hi, you set dsn1_loss、dsn2_loss、dsn3_loss、dsn4_loss、dsn5_loss and fuse_loss. I want to ask if these loss needs backward computation respectively? But I do not know why not sum them? I do not know how do these loss work respectively.I am trying to implement your code in PyTorch. Could you help me ? Thanks a lot!
Sorry, but I can't understand you properly. For deep supervision, maybe you can refer to the paper Deeply-Supervised Nets (AISTATS'15) for theoretical understanding.
Hi, you set dsn1_loss、dsn2_loss、dsn3_loss、dsn4_loss、dsn5_loss and fuse_loss. I want to ask if these loss needs backward computation respectively? But I do not know why not sum them? I do not know how do these loss work respectively.I am trying to implement your code in PyTorch. Could you help me ? Thanks a lot!