W3cubDocs

/TensorFlow Python

tf.keras.backend.ctc_batch_cost

tf.keras.backend.ctc_batch_cost(
    y_true,
    y_pred,
    input_length,
    label_length
)

Defined in tensorflow/python/keras/_impl/keras/backend.py.

Runs CTC loss algorithm on each batch element.

Arguments:

  • y_true: tensor (samples, max_string_length) containing the truth labels.
  • y_pred: tensor (samples, time_steps, num_categories) containing the prediction, or output of the softmax.
  • input_length: tensor (samples, 1) containing the sequence length for each batch item in y_pred.
  • label_length: tensor (samples, 1) containing the sequence length for each batch item in y_true.

Returns:

Tensor with shape (samples,1) containing the CTC loss of each element.

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/keras/backend/ctc_batch_cost