Link Search Menu Expand Document
enuSpace-tensorflow Manual

MatMul

tensorflow C++ API

tensorflow::ops::MatMul

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 forMatMulon GPUs uses cublas.

Arguments:

Optional attributes (seeAttrs):

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

Returns:

Constructor

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

Public attributes

  • tensorflow::Output product

MatMul block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_math.cpp

Argument:

  • Scope scope : A Scope object(A scope is generated automatically each page. A scope is not connected.).
  • Input a : connect Input node.
  • Input b : connect Input node.
  • MatMul::Attrs attrs : Input attrs in value. ex) transpose_a_=true;transpose_b_=false

Return:

  • Output product : Output object of MatMul class object.

Result:

  • std::vector(Tensor) product_result : Returned object of executed result by calling session.

Using Method