Closed HHCorp closed 2 years ago
Thank you for your comment. It is a typo mistake in the paper and we will correct it directly. However, the reported results (in the paper) and the provided training are correct. All results in the paper can be reproduced using the provided code and the pre-trained models.
I guessed this is a typo mistake. Thanks for your reply. The results are reproducible.
First, thanks for your impressive work. I have a small question about the MSEloss formula in your paper. why there is a '1 -' in the formula?