facebookresearch / mixup-cifar10

mixup: Beyond Empirical Risk Minimization
Other
1.17k stars 227 forks source link

No Validation Set #23

Open 07Agarg opened 3 years ago

07Agarg commented 3 years ago

Hi, For supervised methods, it is generally advised to use a separate validation set. From the code, it looks like you have reported the best test set accuracy.

Is there any specific reason that you have not used a separate validation set?