Missed TensorFlow World? Check out the recap. Learn more

tf.nn.ctc_unique_labels

TensorFlow 2.0 version View source on GitHub

Get unique labels and indices for batched labels for tf.nn.ctc_loss.

Aliases:

  • tf.compat.v1.nn.ctc_unique_labels
  • tf.compat.v2.nn.ctc_unique_labels
tf.nn.ctc_unique_labels(
    labels,
    name=None
)

For use with tf.nn.ctc_loss optional argument unique: This op can be used to preprocess labels in input pipeline to for better speed/memory use computing the ctc loss on TPU.

Example:

ctc_unique_labels([[3, 4, 4, 3]]) -> unique labels padded with 0: [[3, 4, 0, 0]] indices of original labels in unique: [0, 1, 1, 0]

Args:

  • labels: tensor of shape [batch_size, max_label_length] padded with 0.
  • name: A name for this Op. Defaults to "ctc_unique_labels".

Returns:

tuple of - unique labels, tensor of shape [batch_size, max_label_length] - indices into unique labels, shape [batch_size, max_label_length]