|TensorFlow 1 version||View source on GitHub|
Computes CTC (Connectionist Temporal Classification) loss.
Compat aliases for migration
See Migration guide for more details.
tf.nn.ctc_loss( labels, logits, label_length, logit_length, logits_time_major=True, unique=None, blank_index=None, name=None )
This op implements the CTC loss as presented in the article:
- Same as the "Classic CTC" in TensorFlow 1.x's tf.compat.v1.nn.ctc_loss setting of preprocess_collapse_repeated=False, ctc_merge_repeated=True
- Labels may be supplied as either a dense, zero-padded tensor with a vector of label sequence lengths OR as a SparseTensor.
- On TPU and GPU: Only dense padded labels are supported.
- On CPU: Caller may use SparseTensor or dense padded labels but calling with a SparseTensor will be significantly faster.
- Default blank label is 0 rather num_classes - 1, unless overridden by blank_index.
||tensor of shape [batch_size, max_label_seq_length] or SparseTensor|
||tensor of shape [frames, batch_size, num_labels], if logits_time_major == False, shape is [batch_size, frames, num_labels].|
||tensor of shape [batch_size], None if labels is SparseTensor Length of reference label sequence in labels.|
||tensor of shape [batch_size] Length of input sequence in logits.|
||(optional) If True (default), logits is shaped [time, batch, logits]. If False, shape is [batch, time, logits]|
||(optional) Unique label indices as computed by ctc_unique_labels(labels). If supplied, enable a faster, memory efficient implementation on TPU.|
||(optional) Set the class index to use for the blank label. Negative values will start from num_classes, ie, -1 will reproduce the ctc_loss behavior of using num_classes - 1 for the blank symbol. There is some memory/performance overhead to switching from the default of 0 as an additional shifted copy of the logits may be created.|
A name for this
||tensor of shape [batch_size], negative log probabilities.|