swapping-autoencoder-pytorch icon indicating copy to clipboard operation
swapping-autoencoder-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon taesungp

some questions about 1024 resolution

Open hughwcq opened this issue 2 years ago • 0 comments

Hi, great work! But I have some questions about 1024 resolution. In the paper: image could you provide the detail about the implemention of smaller network capacity? image And In Appendix B B.3 Datasets: the model is initially trained at 512 x 512 resolution,and finetuned at 1024 resolution. Is the model with smaller network capacity?

hughwcq avatar Jul 06 '22 10:07 hughwcq