This is a try of implementation of the paper 'PairedCycleGAN: Asymmetric Style Transferfor Applying and Removing Makeup' with PyTorch. https://adoberesearch.ctlprojects.com/wp-content/uploads/2018/04/CVPR2018_Paper3623_Chang.pdf
The code is based on the implementation of junyanz's pytorch-CycleGAN-and-pix2pix project https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.
I principally modified the parts of 'model' and 'datasets' .
The dataset and result of training will be uploaded later.
P.S: The code is far away from perfect and may not look like exactly the same as described in the paper but the core ideas are the same.I'm stil working on it.