Apply to speak at TensorFlow World. Deadline April 23rd. Propose talk

tf.contrib.gan.InfoGANModel

Class InfoGANModel

Defined in tensorflow/contrib/gan/python/namedtuples.py.

An InfoGANModel contains all the pieces needed for InfoGAN training.

See https://arxiv.org/abs/1606.03657 for more details.

Args:

  • structured_generator_inputs: A list of Tensors representing the random noise that must have high mutual information with the generator output. List length should match predicted_distributions.
  • predicted_distributions: A list of tfp.distributions.Distributions. Predicted by the recognizer, and used to evaluate the likelihood of the structured noise. List length should match structured_generator_inputs.
  • discriminator_and_aux_fn: The original discriminator function that returns a tuple of (logits, predicted_distributions).

__new__

__new__(
    _cls,
    generator_inputs,
    generated_data,
    generator_variables,
    generator_scope,
    generator_fn,
    real_data,
    discriminator_real_outputs,
    discriminator_gen_outputs,
    discriminator_variables,
    discriminator_scope,
    discriminator_fn,
    structured_generator_inputs,
    predicted_distributions,
    discriminator_and_aux_fn
)

Create new instance of InfoGANModel(generator_inputs, generated_data, generator_variables, generator_scope, generator_fn, real_data, discriminator_real_outputs, discriminator_gen_outputs, discriminator_variables, discriminator_scope, discriminator_fn, structured_generator_inputs, predicted_distributions, discriminator_and_aux_fn)

Properties

generator_inputs

generated_data

generator_variables

generator_scope

generator_fn

real_data

discriminator_real_outputs

discriminator_gen_outputs

discriminator_variables

discriminator_scope

discriminator_fn

structured_generator_inputs

predicted_distributions

discriminator_and_aux_fn