Min Jin Chong
Min Jin Chong
It is possible if you trained with the corresponding dataset.
I am using conda with python 3.7. I have not faced this issue so I'm uncertain how to fix it.
Try setting num_down=4
I've copied a lot of the code from rosalinity stylegan2 so it should support multi-gpu though I have not tested it.
do you mean cat2anime? I really dont know about that, but I have trained a cat2dog version that works decently.
Thanks for sharing, its very cool! Running videos on cpu is definitely very slow. A potential way to speed up might be to batch the operation. In the notebook right...
The network input is a tensor. How you load does not matter. I loaded it with PIL because it plays well with torchvision transforms function which resizes and transforms it...
You could write a dataloader and load the images in batch size of 4.
1) Some layers share the same latent code (like torgb layers) thus even though there are 18 latent codes, there are 26 style modulation layers. 2) It corresponds to the...
The code is written purely in pytorch so this issue seems like incompatibility with pytorch/cuda? Instead of installing using the yaml file, I suggest just installing the pytorch/cuda version that...