Class SparseMatrixSoftmax

java.lang.Object

org.tensorflow.op.RawOp

org.tensorflow.op.linalg.sparse.SparseMatrixSoftmax

All Implemented Interfaces:

Shaped, Op, Operand<TType>

@Operator(group="linalg.sparse")
public final class SparseMatrixSoftmax
extends RawOp
implements Operand<TType>

Calculates the softmax of a CSRSparseMatrix. Calculate the softmax of the innermost dimensions of a SparseMatrix.

Missing values are treated as -inf (i.e., logits of zero probability); and the output has the same sparsity structure as the input (though missing values in the output may now be treated as having probability zero).

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	SparseMatrixSoftmax.Inputs

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
SparseMatrixSoftmax(Operation operation)

Method Summary

Modifier and Type	Method	Description
Output<TType>	asOutput()	Returns the symbolic handle of the tensor.
static <T extends TNumber> SparseMatrixSoftmax	create(Scope scope, Operand<? extends TType> logits, Class<T> type)	Factory method to create a class wrapping a new SparseMatrixSoftmax operation.
Output<? extends TType>	softmax()	Gets softmax.

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, op

Methods inherited from interface Operand

asTensor, shape, type

Methods inherited from interface Shaped

rank, size

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

SparseMatrixSoftmax

public SparseMatrixSoftmax(Operation operation)

Method Details

create

@Endpoint(describeByClass=true)
public static <T extends TNumber>
SparseMatrixSoftmax create(Scope scope,
 Operand<? extends TType> logits,
 Class<T> type)

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

Type Parameters:

T - data type for SparseMatrixSoftmax output and operands

Parameters:

scope - current scope

logits - A CSRSparseMatrix.

type - The value of the type attribute

Returns:

a new instance of SparseMatrixSoftmax

softmax

public Output<? extends TType> softmax()

Gets softmax. A CSRSparseMatrix.

Returns:

softmax.

asOutput

public Output<TType> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of the 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<TType>

See Also:

• OperationBuilder.addInput(Output)