Package org.tensorflow.op.core

Class EditDistance

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.EditDistance

All Implemented Interfaces:

Op, Operand<java.lang.Float>

@Operator
public final class EditDistance
extends PrimitiveOp
implements Operand<java.lang.Float>

Computes the (possibly normalized) Levenshtein Edit Distance.

The inputs are variable-length sequences provided by SparseTensors (hypothesis_indices, hypothesis_values, hypothesis_shape) and (truth_indices, truth_values, truth_shape).

The inputs are:

Nested Class Summary

Nested Classes

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

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
Output<java.lang.Float>	asOutput()	Returns the symbolic handle of a tensor.
static <T> EditDistance	create(Scope scope, Operand<java.lang.Long> hypothesisIndices, Operand<T> hypothesisValues, Operand<java.lang.Long> hypothesisShape, Operand<java.lang.Long> truthIndices, Operand<T> truthValues, Operand<java.lang.Long> truthShape, EditDistance.Options... options)	Factory method to create a class to wrap a new EditDistance operation to the graph.
static EditDistance.Options	normalize(java.lang.Boolean normalize)
Output<java.lang.Float>	output()	A dense float tensor with rank R - 1.

Methods inherited from class java.lang.Object

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

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static <T> EditDistance create(Scope scope,
                                      Operand<java.lang.Long> hypothesisIndices,
                                      Operand<T> hypothesisValues,
                                      Operand<java.lang.Long> hypothesisShape,
                                      Operand<java.lang.Long> truthIndices,
                                      Operand<T> truthValues,
                                      Operand<java.lang.Long> truthShape,
                                      EditDistance.Options... options)

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

Parameters:

scope - current graph scope

hypothesisIndices - The indices of the hypothesis list SparseTensor. This is an N x R int64 matrix.

hypothesisValues - The values of the hypothesis list SparseTensor. This is an N-length vector.

hypothesisShape - The shape of the hypothesis list SparseTensor. This is an R-length vector.

truthIndices - The indices of the truth list SparseTensor. This is an M x R int64 matrix.

truthValues - The values of the truth list SparseTensor. This is an M-length vector.

truthShape - truth indices, vector.

options - carries optional attributes values

Returns:

a new instance of EditDistance

normalize

public static EditDistance.Options normalize(java.lang.Boolean normalize)

Parameters:

normalize - boolean (if true, edit distances are normalized by length of truth).

The output is:

output

public Output<java.lang.Float> output()

A dense float tensor with rank R - 1.

For the example input:

// hypothesis represents a 2x1 matrix with variable-length values: // (0,0) = ["a"] // (1,0) = ["b"] hypothesis_indices = [[0, 0, 0], [1, 0, 0]] hypothesis_values = ["a", "b"] hypothesis_shape = [2, 1, 1]

// truth represents a 2x2 matrix with variable-length values: // (0,0) = [] // (0,1) = ["a"] // (1,0) = ["b", "c"] // (1,1) = ["a"] truth_indices = [[0, 1, 0], [1, 0, 0], [1, 0, 1], [1, 1, 0]] truth_values = ["a", "b", "c", "a"] truth_shape = [2, 2, 2] normalize = true

The output will be:

// output is a 2x2 matrix with edit distances normalized by truth lengths. output = [[inf, 1.0], // (0,0): no truth, (0,1): no hypothesis [0.5, 1.0]] // (1,0): addition, (1,1): no hypothesis

asOutput

public Output<java.lang.Float> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

Specified by:

asOutput in interface Operand<java.lang.Float>

See Also:

OperationBuilder.addInput(Output)