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.

Sign up for GitHub

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

Jump to bottom

about dataset #15

Open
tzhxs opened this issue Oct 18, 2020 · 4 comments
Open

about dataset #15

tzhxs opened this issue Oct 18, 2020 · 4 comments

Comments

@tzhxs
Copy link

tzhxs commented Oct 18, 2020

你好，ImageNet-LT数据集包括“val”, “train” 和 “test”三个文件夹，请问文章中的结果基于val文件夹还是test文件夹
@KaihuaTang
Copy link
Owner

主要结果是test结果，val只用来选超参。report val的表会在图注里单独注明了这是val的结果

@tzhxs
Copy link
Author

tzhxs commented Oct 18, 2020

主要结果是test结果，val只用来选超参。report val的表会在图注里单独注明了这是val的结果

请问imagenet_LT的结果为所有epoch中最优结果还是最后一个epoch的结果

@KaihuaTang
Copy link
Owner

KaihuaTang commented Oct 18, 2020 •
edited
Loading

主要结果是test结果，val只用来选超参。report val的表会在图注里单独注明了这是val的结果

请问imagenet_LT的结果为所有epoch中最优结果还是最后一个epoch的结果

测试test集用的模型是val上最好的epoch。

@tzhxs
Copy link
Author

tzhxs commented Oct 18, 2020

主要结果是test结果，val只用来选超参。report val的表会在图注里单独注明了这是val的结果

请问imagenet_LT的结果为所有epoch中最优结果还是最后一个epoch的结果

测试test集用的模型是val上最好的epoch。

好的，明白了，感谢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@KaihuaTang @tzhxs