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

tune deterministic resnet-50 to 76.3%? #58

Open

dustinvtran opened this issue Aug 16, 2020 · 0 comments

Member

dustinvtran commented Aug 16, 2020 •

edited

Loading

@dustinvtran
Facebook's scaling paper suggests they consistently get 76.4% with base learning rate=0.1 and total_batch_size (kn) = 256, and 76.3% with total_batch_size (kn)=8k. Our accuracies are hovering around 76.0-76.3%, based on the official tpu resnet50 keras codebase. Should double check whether the official codebase is meeting this target and ultimately how we can meet it.

google/edward2#143

dustinvtran mentioned this issue

tune deterministic resnet-50 to 76.3%? google/edward2#143

Closed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment