tf.keras.losses.CTC

CTC (Connectionist Temporal Classification) loss.

Inherits From: Loss

tf.keras.losses.CTC(
    reduction='sum_over_batch_size',
    name='sparse_categorical_crossentropy'
)

Args
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.

Methods

call

View source

call(
    y_true, y_pred
)

from_config

View source

@classmethod
from_config(
    config
)

get_config

View source

get_config()

__call__

View source

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.