LpNormalization

Description

Applies LpNormalization along a given axis of a matrix.

Input

x: input tensor of type float16 or float.

Attribute

axis: int, specifying the axis to be normalized. The value -1 indicates the last axis. Defaults to -1.

p: int, indicating the normalization order. Only 1 or 2 is supported. Default value: 2.

Output

y: output tensor of the identical data type and shape to the input.

Constraints

None.

ONNX Opset Support

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