Add gradient norm target arg to wass gradient penalty function. This trick is usd...
authorA. Unique TensorFlower <gardener@tensorflow.org>
Tue, 13 Feb 2018 16:46:26 +0000 (08:46 -0800)
committerTensorFlower Gardener <gardener@tensorflow.org>
Tue, 13 Feb 2018 16:50:17 +0000 (08:50 -0800)
commit1fc821602d69e5812b854a61f09f163ce549641b
treef53e61ae9a2439b06936583b196fc0104093df4d
parentab9f850f6bba604cfad0d4a2bb11e40517030085
Add gradient norm target arg to wass gradient penalty function. This trick is usd in the progressive GAN paper https://arxiv.org/abs/1710.10196

PiperOrigin-RevId: 185535584
tensorflow/contrib/gan/python/losses/python/losses_impl.py
tensorflow/contrib/gan/python/losses/python/losses_impl_test.py
tensorflow/contrib/gan/python/train.py