stylegan2-tf-2.x

stylegan2-tf-2.x copied to clipboard

Thank you very much for your great work and contribution! I try to get the code running using CUDA Version: 11.6 , Tensorflow 2.8 and Cudnn 8303 When calling the...

dauersuchti

Hi, My dataset is only around 25gb in memory, but after training for a few hours the memory usage is already more than 100gb and it keeps slowly but constantly...

HunorLaczko

NVIDIA updated their [CUDA Linux GPG Repository Key](https://developer.nvidia.com/blog/updating-the-cuda-linux-gpg-repository-key/), the dockerfile creation now crashes. Workaround from [here](https://forums.developer.nvidia.com/t/18-04-cuda-docker-image-is-broken/212892).

Leon-Sander

when training in 256x256, the output is 256x512 pixels

1

First, thanks for this great repository. It is very useful to study the sylegan2 architecture! When training in 256x256 resolution, the output images have a size of 256x512 (h x...

notnot

You ResizeConv2D not work when upsampling, I can't use this module

tom99763

Please update readme

3

Hello, This is a very useful repo. Can you please update readme so one can figure out how to train on custom datasets? Thank you, Siavash

siavash-khodadadeh

Cannot convert pkl file to ckpt when the size is 256 or 512.

5

As title, thanks for your great working! could you tell me how to convert the other size pkl to ckpt.

yuqiu1233

Need help understanding the role of the 'upfirdn' after the transpose_conv

1

Hello, I don't really get the point of the upfirdn (apart from reducing the dim of the height and width of `x` by one)? How is the `resample kernel` chosen?...

NoAchache

different resolution pkl file

1

Hi, When i try to execute inference_from_official_weights, if I put the checkpoint-required files(in official-pretrained folder) for resolutions other than 1024x1024( for eg if i put the pkl file for stylegan2...

nataliaz17