Versioned name: ReduceSum-1
Short description: ReduceSum operation performs reduction with addition of the 1st input tensor in slices specified by the second input.
OpenVINO description: This OP is as same as OpenVINO OP
Description: If set to
Trueit holds axes that are used for reduction. For each such axis, output dimension is equal to 1.
Range of values: True or False
Default value: False
1: Input tensor x of type T1. Required.
2: Scalar or 1D tensor of type T_IND with axis indices for the 1st input along which reduction is performed. Accepted range is
ris the rank of input tensor, all values must be unique, repeats are not allowed. Required.
1: Tensor of the same type as the 1st input tensor and
shape[i] = shapeOf(input1)[i]for all
ithat is not in the list of axes from the second input. For dimensions from the second input tensor,
shape[i] == 1if
keep_dims == True, or
i-th dimension is removed from the output otherwise.
T1: any supported numeric type.
Each element in the output is the result of reduction with addition operation along dimensions specified by the second input:
output[i0, i1, …, iN] = sum[j0,…, jN](x[j0, …, jN]))
Where indices i0, …, iN run through all valid indices for the 1st input and
sum[j0, ..., jN] have
jk = ik for those dimensions
are not in the set of indices specified by the second input of the operation.
When the second input is an empty list, then this operation does nothing, it is an identity.
When the second input contains all dimensions of the 1st input, this means that a single reduction value is calculated for entire input tensor.