StyleGAN2-TensorFlow-2.x
StyleGAN2-TensorFlow-2.x copied to clipboard
Unofficial implementation of StyleGAN2 using TensorFlow 2.x.
This is prob. impossible to track down since there's no stacktrace - but after around 100,000 steps I hit a NaN Value Error that looks like this: ``` Round 128900:...
Thanks for the awesome repo. Just wondering will you add 256x256 FFHQ pretrained model in the future? Or could you point out where to find such pretrained weights for tf2...
The Conv2D op currently does not support grouped convolutions on the CPU. In consequence, when running with CPU, batch size should be 1. Why does CPU not support Conv2D? I...
Added new encoder and deleted the earlier branch to prevent Mac artifacts like MacOSX and .DS_Store
Hello, Firstly, thanks for the great repo. I'm trying to convert your model to tflite. I actually managed to create a .tflite file successfully but when I try to perform...
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?...
Hi @rosasalberto ! Thanks for this awesome library. I was looking through the implementation, and a little bit like [this stylegan encoder](https://github.com/Puzer/stylegan-encoder), was experimenting to build my own in order...
Hi @rosasalberto , Thanks for this amazing tf2 stylegan2 model, it really helps. But when I tried to use FFHQ Discriminator with loaded weights, it didn't predict reasonable results. Instead,...
Hi, i'm getting an error trying to run the example. The error occurs in line `generator = StyleGan2Generator(weights=weights_name, impl=impl, gpu=gpu)` ml/Projects/StyleGAN2-TensorFlow-2.x/dnnlib/_cudacache/upfirdn_2d_f918fb4e29bef8e48ed6562a1427e0f9.so: undefined symbol: _ZNK10tensorflow8OpKernel11TraceStringB5cxx11ERKNS_15OpKernelContextEb Call arguments received by layer 'Conv0_up'...
Hi, thanks for this great update to StyleGAN2 for tf2! I am a teacher and the jupyter notebook that I used in google colab last year to help my students...