Watch talks from the 2019 TensorFlow Dev Summit Watch now

tf.contrib.gan.ACGANModel

Class ACGANModel

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

An ACGANModel contains all the pieces needed for ACGAN training.

See https://arxiv.org/abs/1610.09585 for more details.

Args:

  • one_hot_labels: A Tensor holding one-hot-labels for the batch.
  • discriminator_real_classification_logits: Classification logits for real data.
  • discriminator_gen_classification_logits: Classification logits for generated data.

__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,
    one_hot_labels,
    discriminator_real_classification_logits,
    discriminator_gen_classification_logits
)

Create new instance of ACGANModel(generator_inputs, generated_data, generator_variables, generator_scope, generator_fn, real_data, discriminator_real_outputs, discriminator_gen_outputs, discriminator_variables, discriminator_scope, discriminator_fn, one_hot_labels, discriminator_real_classification_logits, discriminator_gen_classification_logits)

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

one_hot_labels

discriminator_real_classification_logits

discriminator_gen_classification_logits