org.tensorflow.op.core

Class CTCGreedyDecoder

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.CTCGreedyDecoder

All Implemented Interfaces:

Op

@Operator
public final class CTCGreedyDecoder
extends PrimitiveOp

Performs greedy decoding on the logits given in inputs.

A note about the attribute merge_repeated: if enabled, when consecutive logits' maximum indices are the same, only the first of these is emitted. Labeling the blank '*', the sequence "A B B * B B" becomes "A B B" if merge_repeated = True and "A B B B B" if merge_repeated = False.

Regardless of the value of merge_repeated, if the maximum index of a given time and batch corresponds to the blank, index `(num_classes - 1)`, no new element is emitted.

Nested Class Summary

Nested Classes

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

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
static CTCGreedyDecoder	create(Scope scope, Operand<Float> inputs, Operand<Integer> sequenceLength, CTCGreedyDecoder.Options... options) Factory method to create a class to wrap a new CTCGreedyDecoder operation to the graph.
Output<Long>	decodedIndices() Indices matrix, size `(total_decoded_outputs x 2)`, of a `SparseTensor`.
Output<Long>	decodedShape() Shape vector, size `(2)`, of the decoded SparseTensor.
Output<Long>	decodedValues() Values vector, size: `(total_decoded_outputs)`, of a `SparseTensor`.
Output<Float>	logProbability() Matrix, size `(batch_size x 1)`, containing sequence log-probabilities.
static CTCGreedyDecoder.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 CTCGreedyDecoder create(Scope scope,
                                      Operand<Float> inputs,
                                      Operand<Integer> sequenceLength,
                                      CTCGreedyDecoder.Options... options)

Factory method to create a class to wrap a new CTCGreedyDecoder 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_size)`.

options - carries optional attributes values

Returns:

a new instance of CTCGreedyDecoder

mergeRepeated

public static CTCGreedyDecoder.Options mergeRepeated(Boolean mergeRepeated)

Parameters:

mergeRepeated - If True, merge repeated classes in output.

decodedIndices

public Output<Long> decodedIndices()

Indices matrix, size `(total_decoded_outputs x 2)`, of a `SparseTensor`. The rows store: [batch, time].

decodedValues

public Output<Long> decodedValues()

Values vector, size: `(total_decoded_outputs)`, of a `SparseTensor`. The vector stores the decoded classes.

decodedShape

public Output<Long> decodedShape()

Shape vector, size `(2)`, of the decoded SparseTensor. Values are: `[batch_size, max_decoded_length]`.

logProbability

public Output<Float> logProbability()

Matrix, size `(batch_size x 1)`, containing sequence log-probabilities.