python_algorithm

CartoonGAN-Test-Pytorch-Torch

Pytorch and Torch testing code of CartoonGAN [Chen et al., CVPR18]. With the released pretrained models by authors, I made these simple scripts for a quick test.

Getting started

git clone https://github.com/Yijunmaverick/CartoonGAN-Test-Pytorch-Torch
cd CartoonGAN-Test-Pytorch-Torch

Pytorch

The original pretrained models are Torch nngraph models, which cannot be loaded in Pytorch through load_lua. So I manully copy the weights (bias) layer by layer and convert them to .pth models.

• Download the converted models:

  sh pretrained_model/download_pth.sh
  

• For testing:

  python test.py --input_dir YourImgDir --style Hosoda --gpu 0
  

Torch

Working with the original models with Torch is also fine. I just convert the weights (bias) in their models from CudaTensor to FloatTensor so that cudnn is not required for loading models.

• Download the models:

  sh pretrained_model/download_t7.sh
  

• For testing:

  th test.lua -input_dir YourImgDir -style Hosoda -gpu 0
  

Examples (Left: input, Right: output)

Note

• The training code should be similar to the popular GAN-based image-translation frameworks and thus is not included here.

• With a single GPU (~12GB memory), the largest image size for testing is ~500 now.

Acknowledgement

• Many thanks to the authors for this cool work.

• Part of the codes are borrowed from DCGAN, AdaIN and CycleGAN.