search

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
600 stars 100 forks source link

tanh is not applied when im_size < 1024 #11

Closed AtsushiHashimoto closed 3 years ago

AtsushiHashimoto commented 3 years ago

Hi! Thank you for sharing the code of your great work! Our team is enjoying the performance.

By the way, I wonder about the tanh functions applied only with the netG output of im_size==1024 (but not when im_size==256 or im_size==512.

https://github.com/odegeasslbc/FastGAN-pytorch/blob/0e6ea568bc2f39a4e9c599ad9f9fd8f015c341b5/models.py#L177

https://github.com/odegeasslbc/FastGAN-pytorch/blob/0e6ea568bc2f39a4e9c599ad9f9fd8f015c341b5/models.py#L169

I guess that this is not a critical issue but just wanted to let you know.

odegeasslbc commented 3 years ago

Yes, thanks for pointing it out. I was experimenting about the usefulness of tanh and forget to add it back.

AtsushiHashimoto commented 3 years ago

Thanks!