Missed TensorFlow World? Check out the recap. Learn more

tf.contrib.gan.losses.wargs.modified_discriminator_loss

View source on GitHub

Same as minimax discriminator loss.

tf.contrib.gan.losses.wargs.modified_discriminator_loss(
    discriminator_real_outputs,
    discriminator_gen_outputs,
    label_smoothing=0.25,
    real_weights=1.0,
    generated_weights=1.0,
    scope=None,
    loss_collection=tf.GraphKeys.LOSSES,
    reduction=losses.Reduction.SUM_BY_NONZERO_WEIGHTS,
    add_summaries=False
)

See Generative Adversarial Nets (https://arxiv.org/abs/1406.2661) for more details.

Args:

  • discriminator_real_outputs: Discriminator output on real data.
  • discriminator_gen_outputs: Discriminator output on generated data. Expected to be in the range of (-inf, inf).
  • label_smoothing: The amount of smoothing for positive labels. This technique is taken from Improved Techniques for Training GANs (https://arxiv.org/abs/1606.03498). 0.0 means no smoothing.
  • real_weights: Optional Tensor whose rank is either 0, or the same rank as discriminator_gen_outputs, and must be broadcastable to discriminator_gen_outputs (i.e., all dimensions must be either 1, or the same as the corresponding dimension).
  • generated_weights: Same as real_weights, but for discriminator_gen_outputs.
  • scope: The scope for the operations performed in computing the loss.
  • loss_collection: collection to which this loss will be added.
  • reduction: A tf.compat.v1.losses.Reduction to apply to loss.
  • add_summaries: Whether or not to add summaries for the loss.

Returns:

A loss Tensor. The shape depends on reduction.