Class CtcGreedyDecoder<T extends TNumber>

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.nn.CtcGreedyDecoder<T>

All Implemented Interfaces:

Op

@Operator(group="nn")
public final class CtcGreedyDecoder<T extends TNumber>
extends RawOp

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	Description
static class	CtcGreedyDecoder.Inputs<T extends TNumber>
static class	CtcGreedyDecoder.Options	Optional attributes for CtcGreedyDecoder

Field Summary

Fields

Modifier and Type	Field	Description
static final String	OP_NAME	The name of this op, as known by TensorFlow core engine

Fields inherited from class RawOp

operation

Constructor Summary

Constructors

Constructor	Description
CtcGreedyDecoder(Operation operation)

Method Summary

Modifier and Type	Method	Description
static CtcGreedyDecoder.Options	blankIndex(Long blankIndex)	Sets the blankIndex option.
static <T extends TNumber> CtcGreedyDecoder<T>	create(Scope scope, Operand<T> inputs, Operand<TInt32> sequenceLength, CtcGreedyDecoder.Options... options)	Factory method to create a class wrapping a new CTCGreedyDecoder operation.
Output<TInt64>	decodedIndices()	Gets decodedIndices.
Output<TInt64>	decodedShape()	Gets decodedShape.
Output<TInt64>	decodedValues()	Gets decodedValues.
Output<T>	logProbability()	Gets logProbability.
static CtcGreedyDecoder.Options	mergeRepeated(Boolean mergeRepeated)	Sets the mergeRepeated option.

Methods inherited from class RawOp

equals, hashCode, op, toString

Methods inherited from class Object

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

Methods inherited from interface Op

env

Field Details

OP_NAME

public static final String OP_NAME

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

See Also:

• Constant Field Values

Constructor Details

CtcGreedyDecoder

public CtcGreedyDecoder(Operation operation)

Method Details

create

@Endpoint(describeByClass=true)
public static <T extends TNumber>
CtcGreedyDecoder<T> create(Scope scope,
 Operand<T> inputs,
 Operand<TInt32> sequenceLength,
 CtcGreedyDecoder.Options... options)

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

Type Parameters:

T - data type for CTCGreedyDecoder output and operands

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_size).

options - carries optional attribute values

Returns:

a new instance of CtcGreedyDecoder

mergeRepeated

public static CtcGreedyDecoder.Options mergeRepeated(Boolean mergeRepeated)

Sets the mergeRepeated option.

Parameters:

mergeRepeated - If True, merge repeated classes in output.

Returns:

this Options instance.

blankIndex

public static CtcGreedyDecoder.Options blankIndex(Long blankIndex)

Sets the blankIndex option.

Parameters:

blankIndex - the blankIndex option

Returns:

this Options instance.

decodedIndices

public Output<TInt64> decodedIndices()

Gets decodedIndices. Indices matrix, size (total_decoded_outputs x 2), of a SparseTensor<int64, 2>. The rows store: [batch, time].

Returns:

decodedIndices.

decodedValues

public Output<TInt64> decodedValues()

Gets decodedValues. Values vector, size: (total_decoded_outputs), of a SparseTensor<int64, 2>. The vector stores the decoded classes.

Returns:

decodedValues.

decodedShape

public Output<TInt64> decodedShape()

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

Returns:

decodedShape.

logProbability

public Output<T> logProbability()

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

Returns:

logProbability.