aesara.tensor.nnet.ctc
– Connectionist Temporal Classification (CTC) loss¶
Note
Usage of connectionist temporal classification (CTC) loss Op, requires that
the warpctc library is
available. In case the warpctc library is not in your compiler’s library path,
the config.ctc__root
configuration option must be appropriately set to the
directory containing the warpctc library files.
Note
This interface is the preferred interface.
Note
Unfortunately, Windows platforms are not yet supported by the underlying library.

aesara.tensor.nnet.ctc.
ctc
(activations, labels, input_lengths)[source]¶ Compute CTC loss function.
Notes
Using the loss function requires that the Baidu’s warpctc library be installed. If the warpctc library is not on the compiler’s default library path, the configuration variable
config.ctc__root
must be properly set.Parameters:  activations – Threedimensional tensor, which has a shape of (t, m, p), where t is the time index, m is the minibatch index, and p is the index over the probabilities of each symbol in the alphabet. The memory layout is assumed to be in Corder, which consists in the slowest to the fastest changing dimension, from left to right. In this case, p is the fastest changing dimension.
 labels – A 2D tensor of all the labels for the minibatch. In each row, there is a sequence of target labels. Negative values are assumed to be padding, and thus are ignored. Blank symbol is assumed to have index 0 in the alphabet.
 input_lengths – A 1D tensor with the number of time steps for each sequence in the minibatch.
Returns: Cost of each example in the minibatch.
Return type: 1D array

class
aesara.tensor.nnet.ctc.
ConnectionistTemporalClassification
(compute_grad=True, openmp=None)[source]¶ CTC loss function wrapper.
Notes
Using the wrapper requires that Baidu’s warpctc library is installed. If the warpctc library is not on your compiler’s default library path, you must set the configuration variable
config.ctc__root
appropriately.Parameters: compute_grad – If set to True, enables the computation of gradients of the CTC loss function.