tensorflow::ops::SparseMatMul

#include <math_ops.h>

Multiply matrix "a" by matrix "b".

Summary

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 Tensors not SparseTensors. 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.

Arguments:

Returns:

Constructors and Destructors
SparseMatMul(const ::tensorflow::Scope & scope, ::tensorflow::Input a, ::tensorflow::Input b)
SparseMatMul(const ::tensorflow::Scope & scope, ::tensorflow::Input a, ::tensorflow::Input b, const SparseMatMul::Attrs & attrs)

Public attributes
operation
product

Public functions
node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions
AIsSparse(bool x)
BIsSparse(bool x)
TransposeA(bool x)
TransposeB(bool x)

Structs
tensorflow::ops::SparseMatMul::Attrs

Optional attribute setters for SparseMatMul.

Public attributes

operation

Operation operation

product

::tensorflow::Output product

Public functions

SparseMatMul

 SparseMatMul(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input a,
  ::tensorflow::Input b
)

SparseMatMul

 SparseMatMul(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input a,
  ::tensorflow::Input b,
  const SparseMatMul::Attrs & attrs
)

node

::tensorflow::Node * node() const

operator::tensorflow::Input

 operator::tensorflow::Input() const

operator::tensorflow::Output

 operator::tensorflow::Output() const

Public static functions

AIsSparse

Attrs AIsSparse(
  bool x
)

BIsSparse

Attrs BIsSparse(
  bool x
)

TransposeA

Attrs TransposeA(
  bool x
)

TransposeB

Attrs TransposeB(
  bool x
)