-
Notifications
You must be signed in to change notification settings - Fork 130
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
how to set the m and s when there are only 1000 identities? #27
Comments
It's difficult to give you a number. You may try AM Softmax without feature normalization or Auto AM Softmax to avoid setting some of the hyper-parameters. |
But the best accuracy still should be gotten by carefully manually tuned hyper-parameters. |
thanks for your quickly reply! by the way, during the training on VGGFACE2 dataset, how did you define the validation set? select some image from the training set? what was the final loss and the accuracy on the validation set? thanks! |
Don't care about the loss and accuracy. They are meaningless. |
thanks a lot! |
thanks very much for your contribution. i am using gray images to train the model with only about 1000 identities, how need i set the m and s. both of them should be set smaller?
The text was updated successfully, but these errors were encountered: