[Question] What is filter g?
Opened this issue · 6 comments
bjzhb666 commented
JngwenYe commented
it's just a simple selection operation to calculate the related label possibilities. For example, for fc output: [0.1,0.2,0.2,0.5], if we want to preserve the first two labels, g([0.1,0.2,0.2,0.5]) = [0.1,0.2]
bjzhb666 commented
Thanks for your quick reply.
I have another question.
In https://github.com/JngwenYe/LIRF/blob/main/train_deposit.py#L150-L158 , the code does not use criterionAT(output_batch1, output_teacher_batch1.detach())
, is the current version of code use our LIRF method?
which loss do loss1, loss2 and loss3 correspond to in the paper (
bjzhb666 commented
And for the return value in https://github.com/JngwenYe/LIRF/blob/main/train_deposit.py#L174, are two return values the same?