no gradient error when run gan_cifar_resnet.py with BN

igul222 / improved_wgan_training

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

MIT License

2.35k stars 670 forks source link

no gradient error when run gan_cifar_resnet.py with BN #43

Open wangguanan opened 7 years ago

wangguanan commented 7 years ago

When I run gan_cifar_resnet.py with NORMALIZATION_D=True(my tensorflow version is 1.2.0), an error occurred No gradient defined for operation 'gradients/FusedBatchNorm_62_grad/FusedBatchNormGrad' as below:

Can you tell me how to solve it? Thanks!

xunhuang1995 commented 7 years ago

Changing fused to False solves the problem.