Pytorch and Torch testing code of CartoonGAN [Chen et al., CVPR18]
Pytorch and Torch testing code of CartoonGAN
[Chen et al., CVPR18]. With the released pretrained models by the authors, I made these simple scripts for a quick test.
git clone https://github.com/Yijunmaverick/CartoonGAN-Test-Pytorch-Torch cd CartoonGAN-Test-Pytorch-Torch
The original pretrained models are Torch
nngraphmodels, which cannot be loaded in Pytorch through
load_lua. So I manually copy the weights (bias) layer by layer and convert them to
.pthmodels.
sh pretrained_model/download_pth.sh
python test.py --input_dir YourImgDir --style Hosoda --gpu 0
Working with the original models in Torch is also fine. I just convert the weights (bias) in their models from CudaTensor to FloatTensor so that
cudnnis not required for loading models.
sh pretrained_model/download_t7.sh
th test.lua -input_dir YourImgDir -style Hosoda -gpu 0
Many thanks to the authors for this cool work.
Part of the codes are borrowed from DCGAN, TextureNet, AdaIN and CycleGAN.