ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

SparseMatrixMatMul

public final class SparseMatrixMatMul

Matrix-multiplies a sparse matrix with a dense matrix.

Returns a dense matrix. For inputs A and B, where A is CSR and B is dense; this op returns a dense C;

If transpose_output is false, returns:

C = A . B
 
If transpose_output is `true`, returns:
C = transpose(A . B) = transpose(B) . transpose(A)
 
where the transposition is performed along the two innermost (matrix) dimensions.

If conjugate_output is `true`, returns:

C = conjugate(A . B) = conjugate(A) . conjugate(B)
 
If both conjugate_output and transpose_output are `true`, returns:
C = conjugate(transpose(A . B)) = conjugate(transpose(B)) .
                                     conjugate(transpose(A))
 

Nested Classes

class SparseMatrixMatMul.Options Optional attributes for SparseMatrixMatMul  

Public Methods

static SparseMatrixMatMul.Options
adjointA(Boolean adjointA)
static SparseMatrixMatMul.Options
adjointB(Boolean adjointB)
Output<T>
asOutput()
Returns the symbolic handle of a tensor.
static SparseMatrixMatMul.Options
conjugateOutput(Boolean conjugateOutput)
static <T> SparseMatrixMatMul<T>
create(Scope scope, Operand<?> a, Operand<T> b, Options... options)
Factory method to create a class wrapping a new SparseMatrixMatMul operation.
Output<T>
output()
A dense output tensor.
static SparseMatrixMatMul.Options
transposeA(Boolean transposeA)
static SparseMatrixMatMul.Options
transposeB(Boolean transposeB)
static SparseMatrixMatMul.Options
transposeOutput(Boolean transposeOutput)

Inherited Methods

Public Methods

public static SparseMatrixMatMul.Options adjointA (Boolean adjointA)

Parameters
adjointA Indicates whether `a` should be conjugate-transposed.

public static SparseMatrixMatMul.Options adjointB (Boolean adjointB)

Parameters
adjointB Indicates whether `b` should be conjugate-transposed.

public Output<T> asOutput ()

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.

public static SparseMatrixMatMul.Options conjugateOutput (Boolean conjugateOutput)

Parameters
conjugateOutput Conjugates the product of `a` and `b`.

public static SparseMatrixMatMul<T> create (Scope scope, Operand<?> a, Operand<T> b, Options... options)

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

Parameters
scope current scope
a A CSRSparseMatrix.
b A dense tensor.
options carries optional attributes values
Returns
  • a new instance of SparseMatrixMatMul

public Output<T> output ()

A dense output tensor.

public static SparseMatrixMatMul.Options transposeA (Boolean transposeA)

Parameters
transposeA Indicates whether `a` should be transposed.

public static SparseMatrixMatMul.Options transposeB (Boolean transposeB)

Parameters
transposeB Indicates whether `b` should be transposed.

public static SparseMatrixMatMul.Options transposeOutput (Boolean transposeOutput)

Parameters
transposeOutput Transposes the product of `a` and `b`.