pytorch replicate of TP-GAN "Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis"
- I use wasserstein-GP as adversial loss
- I tried adopting modified ReNet18 or MobilNetV2 to extract features to compute perceptual loss (idendity preserving loss in the original paper)
- remove batch normalization layers
- remove the last tanh activation in generator
- change the first conv and the first residual block in decoder of generator's kernel size from 2 to 3
- python3
- tensorboardX
- pytorch 0.3.1
to train feature extract models
vim pretrain_config.py #set options
python pretrain.py
to train TP-GAN
vim config.py #set options
python train.py
to test TP-GAN
python test.py $args
##some other implementations