Watch talks from the 2019 TensorFlow Dev Summit Watch now

tf.contrib.gan.features.clip_variables

tf.contrib.gan.features.clip_variables(
    optimizer,
    variables,
    weight_clip
)

Defined in tensorflow/contrib/gan/python/features/python/clip_weights_impl.py.

Modifies an optimizer so it clips weights to a certain value.

Args:

  • optimizer: An optimizer to perform variable weight clipping.
  • variables: A list of TensorFlow variables.
  • weight_clip: Positive python float to clip discriminator weights. Used to enforce a K-lipschitz condition, which is useful for some GAN training schemes (ex WGAN: https://arxiv.org/pdf/1701.07875).

Returns:

An optimizer to perform weight clipping after updates.

Raises:

  • ValueError: If weight_clip is less than 0.