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
Testing with the best model #8
Comments
I think they choose the model from 100th epoch. |
I think it's much unfair, because the code evenly save the best model. Lines 413 to 414 in 7c84885
We can just use the best model in evaluation :) !! |
I also checked, the selection of the best model doesn't change augmix's performances on test_c. |
Hi @LeeDoYup, there isn't much of a difference between the best and latest models so we just evaluate on the latest model checkpoint. |
I found that cifar.py code does not test the performance with the best model.
augmix/cifar.py
Line 431 in 7c84885
In addition, why the validation set of CIFAR is not used in the model selection ??
The text was updated successfully, but these errors were encountered: