TaiYama
TaiYama
currently our update is made for website and updated model is not open. we planed to make UI for OSS but not yet.
Dont ask entirely different topic from title. Make new Isuues. - the input image size is decided in the code at img2imgdataset.py. so if you want to change you have...
hmm sorry, Im not testing it on windows. If chainer & cupy was normally set-upped , I think it will run.
Maybe you could edit this file directly. https://github.com/pfnet/PaintsChainer/blob/master/run_dependency_test.bat it is only for setup PATH , you can edit for your own PC
hmm how about others feel ??
Thanks for sharing information, personally I think using segmentation information is useful for colorization. Because even human could not know ”actual” color of a sketch, but human can solve segmentation...
hmm. I think Tampopo tend to like use yello because it is near to skin color and low risk color to use it on hair. PaintsChainer could extract some feature...
Yes, the papers in this field is very competitive... Congratulation about your establishment. I also want make more applications and services.
Actually I changed the learning rate manually... for fine tuning. But I dont know it was effective or not.
abbychau made a executable sample but it is not supported officially https://github.com/abbychau/PaintsChainer/releases/tag/v0.1-alpha