-
Stylegan3 Generator can only be used 2 times in an R session when using CUDA, because memory it uses is not released from the GPU (and it uses a lot of memory each time). The CPU version does not have…
-
Hello,
coming from Projected GAN I wanted to test Stylegan-XL. Upon installing/updating all dependencies and wanting to train a model from scratch on my windows PC, I am getting the following Error w…
-
StyleGAN3 is now available.
https://github.com/NVlabs/stylegan3
Do you have plan to support StyleGAN3?
-
As the title says, is it possible to use the training script with a pre-trained SG3 or it will require some adjustments from my side?
By the way, thanks a lot for all your work with inversion!
-
How to use pkl files of official stylegan2 or stylegan3?
-
Why does Discriminator return negative value? I think that Discriminator should return a value between 0 and 1.
```Python
torch.cuda.empty_cache()
script_dir = os.path.abspath('') #
-
I find in your code, you use FP16 for the last 4 layers for stylegan-2. However, you don't activate "torch.cuda.amp"
-
**Describe the bug**
A clear and concise description of what the bug is.
this is report:
(stylegan3) λ python gen_images.py --outdir=out --trunc=1 --seeds=2 --network=https://api.ngc.nvidia.com/v2…
-
**Describe the feature**
**Motivation**
A clear and concise description of the motivation of the feature.
Ex1. It is inconvenient when [....].
Ex2. There is a recent paper [....], which is very …
ZCMax updated
3 years ago
-
I've been slowly working my way through a port of a big Pytorch project to R `torch` (StyleGAN3: https://github.com/NVlabs/stylegan3). I've managed to make my way about half way through the Generator …