tf.contrib.gan.infogan_model( generator_fn, discriminator_fn, real_data, unstructured_generator_inputs, structured_generator_inputs, generator_scope='Generator', discriminator_scope='Discriminator' )
Returns an InfoGAN model outputs and variables.
See https://arxiv.org/abs/1606.03657 for more details.
generator_fn: A python lambda that takes a list of Tensors as inputs and returns the outputs of the GAN generator.
discriminator_fn: A python lambda that takes
generator_inputs. Outputs a 2-tuple of (logits, distribution_list).
logitsare in the range [-inf, inf], and
distribution_listis a list of Tensorflow distributions representing the predicted noise distribution of the ith structure noise.
real_data: A Tensor representing the real data.
unstructured_generator_inputs: A list of Tensors to the generator. These tensors represent the unstructured noise or conditioning.
structured_generator_inputs: A list of Tensors to the generator. These tensors must have high mutual information with the recognizer.
generator_scope: Optional generator variable scope. Useful if you want to reuse a subgraph that has already been created.
discriminator_scope: Optional discriminator variable scope. Useful if you want to reuse a subgraph that has already been created.
An InfoGANModel namedtuple.
ValueError: If the generator outputs a Tensor that isn't the same shape as
ValueError: If the discriminator output is malformed.