Open Howardqlz opened 4 years ago
Hi, i am wonder about this loss: class_loss = class_criterion(class_logit, target_var) / minibatch_size since this loss ignore some samples(no_lable), why here still use the minibatch_size not the labeled_size?
class_loss = class_criterion(class_logit, target_var) / minibatch_size
Hi, i am wonder about this loss:
class_loss = class_criterion(class_logit, target_var) / minibatch_size
since this loss ignore some samples(no_lable), why here still use the minibatch_size not the labeled_size?