Matt ccc1be8857 Adds improved_wgan.py to examples (#75) ...

* Added improved_wgan.py to examples

Implements the improved WGAN with gradient penalty in Keras.

* Fixed PEP8 issues and one docstring mistake.

* Added a note to the discriminator to avoid BatchNormalization, as per the paper.

* Minor docstring correction to clarify description for wasserstein_loss function.

* Fixed a missing line in the generator

* Minor cleanup to make generating the label vectors a bit more elegant.

* Fixing typo in previous commit.

* Moved the model out of a main() function. Model now correctly respects
keras.backend.image_data_format

* Aaaand another PEP8 cleanup >.>

* Gradient penalty is now correctly based on the gradient w.r.t. the input averaged samples, rather than the weights of the discriminator.

* Gradient is now correctly calculated on the output of the discriminator, not the
K.mean() of the output (i.e. the loss).

2017-04-24 23:38:03 -07:00

..

.gitkeep

add empty examples and docs dirs

2017-01-25 10:27:43 +05:30

cifar10_densenet.py

Style fixes (#71)

2017-04-15 09:41:28 -07:00

cifar10_ror.py

Style fixes (#71)

2017-04-15 09:41:28 -07:00

cifar10_wide_resnet.py

Style fixes (#71)

2017-04-15 09:41:28 -07:00

improved_wgan.py

Adds improved_wgan.py to examples (#75)

2017-04-24 23:38:03 -07:00