Skip to contents

CTC (Connectionist Temporal Classification) loss.

Usage

loss_ctc(y_true, y_pred, ..., reduction = "sum_over_batch_size", name = "ctc")

Arguments

y_true

A tensor of shape (batch_size, target_max_length) containing the true labels in integer format. 0 always represents the blank/mask index and should not be used for classes.

y_pred

A tensor of shape (batch_size, output_max_length, num_classes) containing logits (the output of your model). They should not be normalized via softmax.

...

For forward/backward compatability.

reduction

Type of reduction to apply to the loss. In almost all cases this should be "sum_over_batch_size". Supported options are "sum", "sum_over_batch_size" or NULL.

name

String, name for the object

Value

CTC loss value.