pygan.generativeadversarialnetworks package

Submodules

pygan.generativeadversarialnetworks.adversarial_auto_encoders module

class pygan.generativeadversarialnetworks.adversarial_auto_encoders.AdversarialAutoEncoders(gans_value_function=None, feature_matching=False)[source]

Bases: pygan.generative_adversarial_networks.GenerativeAdversarialNetworks

The controller for the Adversarial Auto-Encoders(AAEs).

extract_logs_tuple()[source]

Extract update logs data.

Returns:
  • list of the reconstruction errors.
  • list of probabilities inferenced by the discriminator (mean) in the discriminator’s update turn.
  • list of probabilities inferenced by the discriminator (mean) in the generator’s update turn.
Return type:The shape is
pre_train(generative_model, epochs=300)[source]

Pre-train.

Parameters:
  • generative_model – Generator which draws samples from the fake distribution.
  • epochs – Epochs.
Returnes:
Tuple data. -trained Generator which is-a GenerativeModel. - list of the reconstruction errors.
train(true_sampler, generative_model, discriminative_model, iter_n=100, k_step=10)[source]

Train.

Parameters:
  • true_sampler – Sampler which draws samples from the true distribution.
  • generative_model – Generator which draws samples from the fake distribution.
  • discriminative_model – Discriminator which discriminates true from fake.
  • iter_n – The number of training iterations.
  • k_step – The number of learning of the discriminative_model.
Returns:

Tuple data. - trained Generator which is-a GenerativeModel. - trained Discriminator which is-a DiscriminativeModel.

train_auto_encoder(generative_model, a_logs_list)[source]

Train the generative model as the Auto-Encoder.

Parameters:
  • generative_model – Generator which draws samples from the fake distribution.
  • a_logs_listlist of the reconstruction errors.
Returns:

The tuple data. The shape is… - Generator which draws samples from the fake distribution. - list of the reconstruction errors.

Module contents