ReduceSumSquare

Description

Reduces a dimension of a tensor by calculating the sum of squares of the input tensor elements along the specified axis. If keepdims is set to 1, the rank of the generated tensor is the same as that of the input tensor. If keepdims is set to 0, the generated tensor has the dimension pruned.

Input

data: tensor of type uint32, uint64, int32, int64, float16, double, or float.

Output

reduced data: output tensor of the identical data type to input data.

Attribute

• axes: int list, specifying the calculation axis. Value range: [-r, r–1], where r indicates the rank of the input data.
• keepdims: int, indicating whether to retain the reduced dimension. The default value is 1 (reserved).

Constraints

None

ONNX Opset Support

Opset v1/v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18