ReduceSumSquare

Description

Computes the sum of squares of the input tensor elements along the provided axes.

If keepdim is 1, the rank of the obtained tensor is the same as that of the input tensor. If keepdim is set to 0, the number of dimensions of the obtained tensor is reduced. The above behavior is similar to NumPy, with the exception that NumPy defaults keepdim to False instead of True.

Input

One input:

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

Output

One output:

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

Attribute

axes: The data type is an int list. Meaning: calculation axis. Value range: [-r, r-1], where r is the number of dimensions of the input data x.

keepdims: int. Defaults to 1.

ONNX Opset Support

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