Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

预训练数据集使用问题 #17

Open
yuemingPAN opened this issue Oct 26, 2022 · 3 comments
Open

预训练数据集使用问题 #17

yuemingPAN opened this issue Oct 26, 2022 · 3 comments

Comments

@yuemingPAN
Copy link

您好,datasets.py文件中,args.dataset参数不同会使用不同的预训练数据集,请问vqa_train_filter.json和vqa_train.json有什么不同,当args,dataset==vqav2时,会将vqa_img_feature_train.pickle和vqa_img_feature_val.pickle合并起来做训练,请问您在论文中报告的实验,预训练时具体是用哪种组合呢?比如:pretrain时datasets是vqav2,不做validate, finetune时用okvqa或krvqa

@AndersonStra
Copy link
Owner

args.dataset参数不是预训练数据集参数,是下游微调与测试使用的数据集,vqa_train_filter.json过滤掉了YES/NO 和 number类型的问题。args.dataset直接指定微调时使用的数据集即可

@yuemingPAN
Copy link
Author

好的明白了,谢谢您

@yuemingPAN
Copy link
Author

yuemingPAN commented Oct 26, 2022

大佬再问一下这两个文件有什么区别?
2

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants