-
Notifications
You must be signed in to change notification settings - Fork 54
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
Different architecture of the provided checkpoints #127
Comments
Ya, it makes no difference , and the change is introduced from fix BatchNormalization for QAT, fixing #115. |
Thanks for clarification. Another question: For how many epochs are the pre-trained 'latest_models' for EfficientNet v2S trained for? |
It's 67 epochs, 50 epochs from scratch, and go on trained for another 17 epochs. EffcientNetV2S swish drop_conn 0.2 dropout 0.2 using SGD + L2 regularizer + cosine lr decay + randaug training on MS1MV3 dataset. |
Hi,
Thanks for the great work. I have noticed that the EfficientNetv2S checkpoints provided do not have the exact same last few layers as the code---> output_layer == "F":
The last few layers of the provided checkpoint are:
Whereas, the output_layer = F gives the following:
I understand that this should not make any difference to the model, but is there a particular reason for doing this?
Thanks
The text was updated successfully, but these errors were encountered: