Open bayminbx opened 4 years ago
@bayminbx the results you see here are generated with some other model (not CartoonGAN in fact), the paper will appear on CVPR 2020 and the code and pre-trained model will be released later.
@bayminbx As for the problem you mentioned, I also came across when I was training the original CartoonGAN. Maybe you can try increasing the weight of content loss.
hi, how do you solve the "multi scale" problem? I train the network with size 256 face images, but in inference the size of images is 512. The result is bad. Can you give me some advice?Thank you.
New model is open-sourced, maybe you can try that one: https://github.com/SystemErrorWang/White-box-Cartoonization
when I train cartoongan(use face images and real_world images), some strange color appear on the face. And in cartoon face images, big eyes are usual.Can you give me some advice?