facebookresearch / mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question regarding figure 5 on the paper

ajboloor opened this issue · comments

What pipeline was used to report the finetuned accuracy numbers on fig. 5 of the paper?

Specifically, when is the masking done?
Is it done only during pretraining?

Or is it done also during finetuning?