-
Notifications
You must be signed in to change notification settings - Fork 18
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
Supervised Metric Pretraining #2
base: master
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks a lot for your work. But maybe you should address the following two concerns before the PR is merged.
- You should reformat the code to make it clean.
- Maybe you should make it runnable.
aab4948
to
7a10c29
Compare
Thank you, I refactored it and included a sample code for imagenet dataset. |
Thanks a lot for your quick reply. |
Hello,
I am writing from my first account. I would like to add an option for supervised metric pretraining. It is used with LinearAverage from LinearAverage.py since the output is expected to be passed to this class. It performs eq. (4) as mentioned in https://arxiv.org/pdf/1812.08781.pdf. Also, I found using the temperature parameter handy, as mentioned in https://arxiv.org/pdf/1805.01978.pdf. Thanks for your consideration.