You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for your impressive contribution so much. I have one question when training this model.
When I set the no_jsd to True/False (cifar 100) using python cifar.py to get table 4, I got a 36.073(published 39.8) for no_jsd=True and 35.895(published 35.9). Do you have any idea why I got such a huge difference when setting the no_jsd to True?
The text was updated successfully, but these errors were encountered:
It may be noise; I should say we did not run with the exact code used in this repository, but it should be representative enough. I expect that the perturbation stability and calibration is quite improved by the JSD loss. If you found it didn't help with corrupution robustness, perturbation stability, or calibration on CIFAR-10 and CIFAR-100, then there is a bug. If you suspect a bug let us know.
Thanks for your impressive contribution so much. I have one question when training this model.
When I set the no_jsd to True/False (cifar 100) using python cifar.py to get table 4, I got a 36.073(published 39.8) for no_jsd=True and 35.895(published 35.9). Do you have any idea why I got such a huge difference when setting the no_jsd to True?
The text was updated successfully, but these errors were encountered: