SparseMatMul

public final class SparseMatMul

Multiply matrix "a" by matrix "b".

The inputs must be two-dimensional matrices and the inner dimension of "a" must match the outer dimension of "b". Both "a" and "b" must be `Tensor`s not `SparseTensor`s. This op is optimized for the case where at least one of "a" or "b" is sparse, in the sense that they have a large proportion of zero values. The breakeven for using this versus a dense matrix multiply on one platform was 30% zero values in the sparse matrix.

The gradient computation of this operation will only take advantage of sparsity in the input gradient when that gradient comes from a Relu.

Nested Classes

class SparseMatMul.Options Optional attributes for SparseMatMul

Constants

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

Public Methods

static SparseMatMul.Options
aIsSparse (Boolean aIsSparse)
Output < TFloat32 >
asOutput ()
Returns the symbolic handle of the tensor.
static SparseMatMul.Options
bIsSparse (Boolean bIsSparse)
static SparseMatMul
create ( Scope scope, Operand <? extends TNumber > a, Operand <? extends TNumber > b, Options... options)
Factory method to create a class wrapping a new SparseMatMul operation.
Output < TFloat32 >
static SparseMatMul.Options
transposeA (Boolean transposeA)
static SparseMatMul.Options
transposeB (Boolean transposeB)

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "SparseMatMul"

Public Methods

public static SparseMatMul.Options aIsSparse (Boolean aIsSparse)

public Output < TFloat32 > asOutput ()

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.

public static SparseMatMul.Options bIsSparse (Boolean bIsSparse)

public static SparseMatMul create ( Scope scope, Operand <? extends TNumber > a, Operand <? extends TNumber > b, Options... options)

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

Parameters
scope current scope
options carries optional attributes values
Returns
  • a new instance of SparseMatMul

public Output < TFloat32 > product ()

public static SparseMatMul.Options transposeA (Boolean transposeA)

public static SparseMatMul.Options transposeB (Boolean transposeB)