TFC-pretraining icon indicating copy to clipboard operation
TFC-pretraining copied to clipboard

Published 20 hours ago • verified publisher icon mims-harvard

some details questions

Open yuyunannan opened this issue 1 year ago • 4 comments

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 avatar Mar 16 '23 08:03 yuyunannan

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

yuyunannan avatar Mar 21 '23 00:03 yuyunannan

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

zzj2404 avatar Mar 21 '23 10:03 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

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

1057699668 avatar Mar 30 '23 02:03 1057699668

same problem

juntaozhang avatar May 06 '23 08:05 juntaozhang