Pytorch implementation of the DCGAN paper and Improved Techniques for Training GANs. Currently, only feature matching is implemented. Minibatch discrimination, label smoothing and historical averaging will be implemented soon.
Put your images in a folder and specify path to that folder in config/hyperparameters.yaml. Also, other training configurations can be modified in the file. Then run python main.py.
Training progress will be logged in WandB.
- Minibatch discrimination
- Label smoothing
- Historical averaging