Dianmo Sheng

> Thanks for your brilliant work, and when I run predict.py, the errors occured. > > Detectron v2 is not installed mismatched input '(' expecting See https://hydra.cc/docs/next/advanced/override_grammar/basic for details >...

> Hi! > > That's strange... The lines about detectron and matplotlib are just warnings, they should not break anything. > > Did you check the versions of the libraries...

@windj007 I'm facing with the same problem after training 40 epoch on FFHQ dataset. However,the artifacts are much more obvious, any idea to alleviate the problem? https://s2.loli.net/2022/03/08/ZiBMduyKPJporVF.jpg

> @ImmortalSdm is this image from training dataloader or from validation? If this is validation, then such artifacts may apper when the mask is non-binary, e.g. it has smooth transition...

> Hi, > > I tried to run the example and get following error. Could you please help with it? Thank you. > > Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing......

> What is your tf version? 1.14.0

@zsyzzsoft I'm facing worse result after 2960k iter. Any ideas？ https://s2.loli.net/2022/03/13/u8qtRLrPWwgBGyZ.png Besides, is the fake_init normal? Seems the masks are not binary. https://s2.loli.net/2022/03/13/O7SwvqP9Mh3TmKl.png

> If the FID metric suddenly spikes up at some iteration, you can try resume training from the last normal checkpoint. Sometimes this happens because of GPU issue. The fake_init...

@lyndonzheng > Hello, thank you for releasing the code. I really appreciate your work. I am trying to train this model on a custom dataset. But I don't know how...

How to deal with the chekpoints? When using "tar -xvf", raising error "tar: This does not look like a tar archive"