Pytorch-Attention-Guided-CycleGAN icon indicating copy to clipboard operation
Pytorch-Attention-Guided-CycleGAN copied to clipboard

Published 20 hours ago • verified publisher icon alokwhitewolf

Implemenetation and paper differences

Open Tymyan1 opened this issue 5 years ago • 0 comments

Very clean code, however I have found what I believe are differences between the paper and the code implementation in the model structure. Could you please share why these differences came into existence?

  1. According to Apendix A the last layer of generator should be c3s1-3-T, but rather c7s1-3-T is used in the code.
  2. The second up-scaling layer in the attention network is commented out (and having this in would mean the following conv should have stride 2?)
  3. The resblocks do not seem to relu the output and while the paper does not mention anything (just says use resblock), from what I know about them, the (out+x) should be passed through relu?
  4. Missing the s′new part of equation num 6?

Tymyan1 avatar May 10 '19 10:05 Tymyan1