CtcBeamSearchDecoder

public final class CtcBeamSearchDecoder

Performs beam search decoding on the logits given in input.

A note about the attribute merge_repeated: For the beam search decoder, this means that if consecutive entries in a beam are the same, only the first of these is emitted. That is, when the top path is "A B B B B", "A B" is returned if merge_repeated = True but "A B B B B" is returned if merge_repeated = False.

Nested Classes

class CtcBeamSearchDecoder.Options Optional attributes for CtcBeamSearchDecoder  

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

static <T extends TNumber> CtcBeamSearchDecoder<T>
create(Scope scope, Operand<T> inputs, Operand<TInt32> sequenceLength, Long beamWidth, Long topPaths, Options... options)
Factory method to create a class wrapping a new CtcBeamSearchDecoder operation.
List<Output<TInt64>>
decodedIndices()
A list (length: top_paths) of indices matrices.
List<Output<TInt64>>
decodedShape()
A list (length: top_paths) of shape vector.
List<Output<TInt64>>
decodedValues()
A list (length: top_paths) of values vectors.
Output<T>
logProbability()
A matrix, shaped: `(batch_size x top_paths)`.
static CtcBeamSearchDecoder.Options
mergeRepeated(Boolean mergeRepeated)

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "CTCBeamSearchDecoder"

Public Methods

public static CtcBeamSearchDecoder<T> create (Scope scope, Operand<T> inputs, Operand<TInt32> sequenceLength, Long beamWidth, Long topPaths, Options... options)

Factory method to create a class wrapping a new CtcBeamSearchDecoder operation.

Parameters
scope current scope
inputs 3-D, shape: `(max_time x batch_size x num_classes)`, the logits.
sequenceLength A vector containing sequence lengths, size `(batch)`.
beamWidth A scalar >= 0 (beam search beam width).
topPaths A scalar >= 0, <= beam_width (controls output size).
options carries optional attributes values
Returns
  • a new instance of CtcBeamSearchDecoder

public List<Output<TInt64>> decodedIndices ()

A list (length: top_paths) of indices matrices. Matrix j, size `(total_decoded_outputs[j] x 2)`, has indices of a `SparseTensor`. The rows store: [batch, time].

public List<Output<TInt64>> decodedShape ()

A list (length: top_paths) of shape vector. Vector j, size `(2)`, stores the shape of the decoded `SparseTensor[j]`. Its values are: `[batch_size, max_decoded_length[j]]`.

public List<Output<TInt64>> decodedValues ()

A list (length: top_paths) of values vectors. Vector j, size `(length total_decoded_outputs[j])`, has the values of a `SparseTensor`. The vector stores the decoded classes for beam j.

public Output<T> logProbability ()

A matrix, shaped: `(batch_size x top_paths)`. The sequence log-probabilities.

public static CtcBeamSearchDecoder.Options mergeRepeated (Boolean mergeRepeated)

Parameters
mergeRepeated If true, merge repeated classes in output.