org.tensorflow.op.core

Class CTCBeamSearchDecoder

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.CTCBeamSearchDecoder

All Implemented Interfaces:

Op

@Operator
public final class CTCBeamSearchDecoder
extends PrimitiveOp

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 Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CTCBeamSearchDecoder.Options Optional attributes for CTCBeamSearchDecoder

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
static CTCBeamSearchDecoder	create(Scope scope, Operand<Float> inputs, Operand<Integer> sequenceLength, Long beamWidth, Long topPaths, CTCBeamSearchDecoder.Options... options) Factory method to create a class to wrap a new CTCBeamSearchDecoder operation to the graph.
List<Output<Long>>	decodedIndices() A list (length: top_paths) of indices matrices.
List<Output<Long>>	decodedShape() A list (length: top_paths) of shape vector.
List<Output<Long>>	decodedValues() A list (length: top_paths) of values vectors.
Output<Float>	logProbability() A matrix, shaped: `(batch_size x top_paths)`.
static CTCBeamSearchDecoder.Options	mergeRepeated(Boolean mergeRepeated)

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static CTCBeamSearchDecoder create(Scope scope,
                                          Operand<Float> inputs,
                                          Operand<Integer> sequenceLength,
                                          Long beamWidth,
                                          Long topPaths,
                                          CTCBeamSearchDecoder.Options... options)

Factory method to create a class to wrap a new CTCBeamSearchDecoder operation to the graph.

Parameters:

scope - current graph 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

mergeRepeated

public static CTCBeamSearchDecoder.Options mergeRepeated(Boolean mergeRepeated)

Parameters:

mergeRepeated - If true, merge repeated classes in output.

decodedIndices

public List<Output<Long>> 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].

decodedValues

public List<Output<Long>> 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.

decodedShape

public List<Output<Long>> 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]]`.

logProbability

public Output<Float> logProbability()

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