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

Different image standardizations for 2017 and 2018 models #2

Open
zhenglilei opened this issue May 21, 2019 · 1 comment
Open

Different image standardizations for 2017 and 2018 models #2

zhenglilei opened this issue May 21, 2019 · 1 comment

Comments

@zhenglilei
Copy link

Thanks for this useful tool for converting facenet-tensorflow to facenet-caffe!

About the models, an important factor may have been ignored when do inference.
20170512-110547: per_image_standardization (the prewhiten function in your codes)
20180402-114759: fixed_standardization

With the correct standardization used, the 2018 model shall perform better than the 2017 model.

I also put this notice at the original FaceNet issue pool: davidsandberg/facenet#948 (comment)

@taylorlu
Copy link
Owner

Good job, I'll take some time to look into it.

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