|View source on GitHub|
Modified generator loss for GANs.
tf.contrib.gan.losses.wargs.modified_generator_loss( discriminator_gen_outputs, label_smoothing=0.0, weights=1.0, scope=None, loss_collection=tf.GraphKeys.LOSSES, reduction=losses.Reduction.SUM_BY_NONZERO_WEIGHTS, add_summaries=False )
L = -log(sigmoid(D(G(z))))
This is the trick used in the original paper to avoid vanishing gradients
early in training. See
Generative Adversarial Nets
(https://arxiv.org/abs/1406.2661) for more details.
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).
0.0means no smoothing.
Tensorwhose rank is either 0, or the same rank as
discriminator_gen_outputs, and must be broadcastable to
labels(i.e., all dimensions must be either
1, or the same as the corresponding dimension).
scope: The scope for the operations performed in computing the loss.
loss_collection: collection to which this loss will be added.
tf.compat.v1.losses.Reductionto apply to loss.
add_summaries: Whether or not to add summaries for the loss.
A loss Tensor. The shape depends on