ReduceMean

Description

Calculates the mean value of elements in a specified dimension of the input tensor.

Input

One input:

x: tensor of type float16 or float.

Output

One output:

y: tensor of the identical data type and format as input x.

Property

axes: a 1D list of integers, specifying the dimension to be reduced. The value range is [-r, r - 1], where r indicates the rank of the input matrix.

keepdims: int. Defaults to 1, meaning that the reduced dimensions are retained.

ONNX Opset Support

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