MeanVarianceNormalization

Description

Normalize the mean and variance of the input tensorX using the following formula: (X-EX)/sqrt(E(X-EX)^2).

Input

One input:

x: list of tensors of type float16 or float.

Output

One output:

y: list of tensors of type float16 or float.

Property

axes: list of ints. Defaults to ['0', '2', '3'].

ONNX Opset Support

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