tf.keras.backend.ctc_batch_cost

Runs CTC loss algorithm on each batch element.

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.backend.ctc_batch_cost, `tf.compat.v2.keras.backend.ctc_batch_cost`

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

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.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2020-10-01 UTC.

Arguments