Shuai Yang
Shuai Yang
I seem that I can open the colab link.
mask is the shape. content feature is used to predict the mask.
Our pretrained encoder works for non-ImageNet images, such as MS-COCO giraffes, Yosemite landscapes and Artistic portraits. I think you can try the pretrained encoder first to see whether it also...
I haven't tried this task. I think no architecture needs to be changed. You could consider adding some losses such as reconstruction loss to improve the performance on restoration task.
I upload the file for evaluation https://github.com/williamyang1991/GP-UNIT/blob/main/notebooks/evaluation.ipynb
https://github.com/williamyang1991/DualStyleGAN/issues/39#issuecomment-1205487616 Here is a solution
you need to train a StyleGAN on full body images or use a [pre-trained one](https://github.com/stylegan-human/StyleGAN-Human/) Then you need to train DualStyleGAN based on this StyleGAN on full body cartoon images.
1. It's module error, not model error 2. you need to change the code of stylegan to support 512*1024
I see... Our backbone is rosinality's stylegan2-pytorch, and can only load the model in its format. So you need to transform the model format from others' framework (tensorflow or official...
> you need to train a StyleGAN on full body images. > Then you need to train DualStyleGAN based on this StyleGAN on full body cartoon images. Please refer to...