tensorflow::ops::MatMul

#include <math_ops.h>

Multiply the matrix "a" by the matrix "b".

Summary

The inputs must be two-dimensional matrices and the inner dimension of "a" (after being transposed if transpose_a is true) must match the outer dimension of "b" (after being transposed if transposed_b is true).

Note: The default kernel implementation for MatMul on GPUs uses cublas.

Arguments:

• scope: A Scope object

Optional attributes (see Attrs):

• transpose_a: If true, "a" is transposed before multiplication.
• transpose_b: If true, "b" is transposed before multiplication.

Returns:

• Output: The product tensor.

Public attributes

::tensorflow::Output product

Public functions

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

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

::tensorflow::Node * node() const 

operator::tensorflow::Input() const 

operator::tensorflow::Output() const 

Public static functions

Attrs TransposeA(
  bool x
)

Attrs TransposeB(
  bool x
)