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

Do you need image alignment during training or evalution? #8

Closed
x7177214 opened this issue Oct 9, 2018 · 7 comments
Closed

Do you need image alignment during training or evalution? #8

x7177214 opened this issue Oct 9, 2018 · 7 comments

Comments

@x7177214
Copy link

x7177214 commented Oct 9, 2018

Thanks.

@x7177214
Copy link
Author

x7177214 commented Oct 9, 2018

I am also wondering what the dataset you used to pretrain Mobilefacenet. Thanks.

@TreB1eN
Copy link
Owner

TreB1eN commented Oct 10, 2018

yes, you can see from the codes, alignment is through MTCNN

@x7177214
Copy link
Author

thanks

@x7177214
Copy link
Author

I am also wondering what the dataset you used to pretrain Mobilefacenet. Thanks.

@TreB1eN
Copy link
Owner

TreB1eN commented Oct 12, 2018

emore dataset, I think it's a variation of MSCELEB, you can see more from this discussion

deepinsight/insightface#215

@x7177214
Copy link
Author

Thanks.

@TreB1eN TreB1eN closed this as completed Oct 20, 2018
@TreB1eN
Copy link
Owner

TreB1eN commented Oct 20, 2018

closing

bogdan-veliscu added a commit to tomasic/arcface_torch that referenced this issue Oct 20, 2020
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