Open Phuoc-Hoan-Le opened 2 years ago
Hi @CharlesLeeeee, Thanks for your message. No the hparams are not the same (see here for more details). Best, Hugo
Hi @TouvronHugo, I noticed that those hyperparameters are from 2021, which I believe is pre DeiT III. I was wondering if you use the same finetuning hyperparameters for DeiT III, or if something else is used? Thank you!
Cannot find it in the paper? Is it the same as training on imagenet?