SystemErrorWang

@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.

New model is open-sourced， maybe you can try that one: https://github.com/SystemErrorWang/White-box-Cartoonization

@yxt132 gtx 1080ti has 11gb gpu memory and i think it's enough to train this network. In fact I managed to train this network in my gtx1070 laptop. The out...

@TotalKoshmar It's OK use this code to produce videos and upload to Youtube, but please specify the resource.

@sayakpaul Thank you for your tutorial!

would like to know if the dataset is available now? I am looking forward to see the inpainting dataset!

> Thanks @hariharans29 ; @prasanthpul are there any plans in fixing this model so it can run out of the box without having to rely on the node attribute rewrite...

Hi @USTClj , I tried to train this model on some other dataset for 20000 epoch and got the results almost the same as the inputs, and also noticed that...

I read the post mentioned by @zhengkang86 , and found some tips about training: 1. Initialization of G First we initialized G only with the self-regularization loss so that it...

Same problem here, use win10 64bit, gtx1070 gpu, cuda 8.0, python3.6 and tensorflow-gpu 1.3. Tried to search the internet but got nothing worth mention. Would like to know if there...