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
In order to tune the neural network to get better performance, I am considering following the steps mentioned in the paper 'Training tips for Tranformer model'-https://arxiv.org/abs/1804.00247.
However, this article is based on the NLP task and original Transformer architecture instead of ViT. Do you think these tricks are still useful?
The text was updated successfully, but these errors were encountered:
Thank you very much for sharing your great work!
In order to tune the neural network to get better performance, I am considering following the steps mentioned in the paper 'Training tips for Tranformer model'-https://arxiv.org/abs/1804.00247.
However, this article is based on the NLP task and original Transformer architecture instead of ViT. Do you think these tricks are still useful?
The text was updated successfully, but these errors were encountered: