An attempt to generate industry-standard facial images for anime characters using Generative Adversarial Networks
- Self Attention Module + hinge loss
- Conditional Batch Normalization
- Big GAN + residual blocks
- Instance Noise
- Tensorboard visualization
SAGAN V2 Epoch 217
SAGAN with INSTANCE NOISE
SAGAN V1 | SAGAN V2 |
---|---|
SAGAN with INSTANCE NOISE
- Python 3.7.3
- Pytorch 1.2.0
- Numpy 1.17.2
- BCE Loss
- Tagging Data
- Get Big GAN to work?