Why use nearest mode in UpBlock?

odegeasslbc / FastGAN-pytorch

Official implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis" in ICLR 2021

GNU General Public License v3.0

606 stars 100 forks source link

Open mar-cry opened 1 year ago

mar-cry commented 1 year ago

Thanks for your excellent work. I want to ask why use nearest mode in nn.Upsample layer in UpBlock in Generator, rather than linear or bilinear mode?