tf.contrib.gan

 

upper level

 

Modules

 

estimator:

TFGAN estimator module.

eval:

TFGAN evaluation module.

features:

TFGAN features module.

losses:

TFGAN losses and penalties.

 

Classes

 

ACGANModel:

An ACGANModel contains all the pieces needed for ACGAN training.

CycleGANLoss:

CycleGANLoss contains the losses for CycleGANModel.

CycleGANModel:

An CycleGANModel contains all the pieces needed for CycleGAN training.

GANLoss:

GANLoss contains the generator and discriminator losses.

GANModel:

A GANModel contains all the pieces needed for GAN training.

GANTrainOps:

GANTrainOps contains the training ops.

GANTrainSteps:

Contains configuration for the GAN Training.

InfoGANModel:

An InfoGANModel contains all the pieces needed for InfoGAN training.

RunTrainOpsHook:

A hook to run train ops a fixed number of times.

 

Functions

 

acgan_model(…):

Returns an ACGANModel contains all the pieces needed for ACGAN training.

cyclegan_loss(…):

Returns the losses for a CycleGANModel.

cyclegan_model(…):

Returns a CycleGAN model outputs and variables.

gan_loss(…):

Returns losses necessary to train generator and discriminator.

gan_model(…):

Returns GAN model outputs and variables.

gan_train(…):

A wrapper around contrib.training.train that uses GAN hooks.

gan_train_ops(…):

Returns GAN train ops.

get_joint_train_hooks(…):

Returns a hooks function for sequential GAN training.

get_sequential_train_hooks(…):

Returns a hooks function for sequential GAN training.

get_sequential_train_steps(…):

Returns a thin wrapper around slim.learning.train_step, for GANs.

infogan_model(…):

Returns an InfoGAN model outputs and variables.