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

How does ATTA implement imagenet training? #2

Open
jaewonalive opened this issue Jan 20, 2023 · 0 comments
Open

How does ATTA implement imagenet training? #2

jaewonalive opened this issue Jan 20, 2023 · 0 comments

Comments

@jaewonalive
Copy link

Hi,

I'm greatly impressed by your paper.

However, I have one question.

In the paper, you said ATTA is much faster than free in imagenet.

You didn't publish imagenet training code.

In CIFAR 10 code, you load all training data in GPU memory.

Imagenet is huge data. So you may not load all your training data in GPU memory.

How did you implement ATTA in imagenet?
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
1 participant
@jaewonalive