This is an implementation of a unpaired MakeUp Generator Architecture for GAN on tensorflow. The model generates makeup image from no-makeup face or vice versa.

• (BeautyGAN.py, config.py): These files are the main MakeupGAN network.

• (datapipe.py): This file's role is loading and changing to tensor your dataset taht are in makeup_dataset folder which is consist of image and segs(mask) folder. The image folder contain makeup image and no-makeup image folder and the segs folder have 3 partial region that are eye, shadow, lips.

• (pretrained_models): you put the pretrained (VGG 19) model in this folder.

• (train.py): this file is for training. To train this network ''' python train.py '''

• (inference.py): this file is for inference. we have 2 inference mode that are reference style and random style and you set True or False on --rand_style value. To run this file ''' python infernece.py '''

no-makeup	makeup
Generated makeup image	Generated no-makeup image