Skip to content

Implementation details of Disjoint CIFAR-10 #4

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
Open
phquang opened this issue May 9, 2020 · 0 comments
Open

Implementation details of Disjoint CIFAR-10 #4

phquang opened this issue May 9, 2020 · 0 comments

Comments

@phquang
Copy link

phquang commented May 9, 2020 •
edited
Loading

Hi,
I want to clarify some implementation details in the paper versus the configuration provided here for the Disjoint CIFAR-10 benchmark:

  1. The backbone used is reduced Resnet18 instead of a full Resnet18
  2. The total amount of training data is 50,000 (10,000 per task) instead of total 10k (2k per task)
  3. The total amount of data stored is 1,000 (averaged 200 per task)
    Thank you
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
@phquang