some details questions

[yuyunannan]

I have a problem. When I get one_hot_encode for my fine 275 line, Should I write
onehot_label = F.one_hot(labels,config.num_classes_target)
instead of
onehot_label = F.one_hot(labels)

[yuyunannan]

I have another small question, may I ask if the best result of the paper is obtained in the case of subset=True?

[zzj2404]

I have another small question, may I ask if the best result of the paper is obtained in the case of subset=True?

I have same problem, if I set subset=False, pretrain loss even don't descend

[1057699668]

I have another small question, may I ask if the best result of the paper is obtained in the case of subset=True?

I have same problem, if I set subset=False, pretrain loss even don't descend

Me too. I hope the author can answer this doubt for us.

[juntaozhang]

same problem