Class ov::op::v1::ReduceSum#

class ReduceSum : public ov::op::util::ArithmeticReductionKeepDims#

Tensor sum operation.

Element-wise sums the input tensor, eliminating the specified reduction axes. For example:

$$\begin{array}{r}\mathit{sum}(\{0\},\left[\begin{array}{cc}1& 2\\ 3& 4\\ 5& 6\end{array}\right])=[(1+3+5),(2+4+6)]=[9,12]\text{(dimension 0 (rows) is eliminated)}\end{array}$$

$$\begin{array}{r}\mathit{sum}(\{1\},\left[\begin{array}{cc}1& 2\\ 3& 4\\ 5& 6\end{array}\right])=[(1+2),(3+4),(5+6)]=[3,7,11]\text{(dimension 1 (columns) is eliminated)}\end{array}$$

$$\begin{array}{r}\mathit{sum}(\{0,1\},\left[\begin{array}{cc}1& 2\\ 3& 4\\ 5& 6\end{array}\right])=(1+2)+(3+4)+(5+6)=21\text{(both dimensions (rows and columns) are eliminated)}\end{array}$$

Parameters

	Description
reduction_axes	The axes to eliminate through summation.
keep_dims	If set to 1 it holds axes that are used for reduction.

Inputs

	Type	Description
arg	$N[d_1,\dots ,d_n](n\ge 0)$	An input tensor of any shape and numeric element type.

Type	Description
$N[\mathit{\text{delete}}(A,d_1,\dots ,d_n)]$	The tensor $T$, where $T$ is the input tensor with the reduction_axes $A$ eliminated by summation.

Public Functions

ReduceSum() = default#

Constructs a summation operation.

ReduceSum(const Output<Node> &arg, const Output<Node> &reduction_axes, bool keep_dims = false)#

Constructs a summation operation.

Parameters:

• arg – The tensor to be summed.

• reduction_axes – The axis positions (0-based) to be eliminated.

• keep_dims – If set to 1 it holds axes that are used for reduction.

virtual bool has_evaluate() const override#

Allows to get information about availability of evaluate method for the current operation.