MNIST example is missing batchnorm for DCGAN

igul222 / improved_wgan_training

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

MIT License

2.35k stars 670 forks source link

MNIST example is missing batchnorm for DCGAN #23

Open marc-tonsen opened 7 years ago

marc-tonsen commented 7 years ago

In the MNIST example the batch normalization is only added for mode 'wgan', which seems to break the example when run in mode 'dcgan'. Adding batch normalization in mode 'dcgan' too fixes it.