tf.contrib.gan.features.condition_tensor_from_onehot( tensor, one_hot_labels, embedding_size=256 )
Condition a tensor based on a one-hot tensor.
Conditioning scheme based on https://arxiv.org/abs/1609.03499.
tensor: Tensor to be conditioned.
one_hot_labels: A Tensor of one-hot labels. Shape is [batch_size, num_classes].
embedding_size: The size of the class embedding.
tensor conditioned on
one_hot_labelsisn't 2D, if non-batch dimensions aren't fully defined, or if batch sizes don't match.