ShoufaChen / AdaptFormer

[NeurIPS 2022] Implementation of "AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition"

Home Page:https://arxiv.org/abs/2205.13535

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Questions about data split.

luogen1996 opened this issue · comments

Thanks for your great work. I would like to know on which data split (val or test) the performance is reported in your paper. I notice that the final testing seems to be conducted on validation set.

mode = 'test'
anno_path = os.path.join(args.data_path, 'val.csv') 

Yes, for SSv2 dataset, the final testing is also conducted on val.csv, which follows the VideoMAE settings.