name: LpNormalization (GitHub)
shape inference: True
This version of the operator has been available since version 1.
Given a matrix, apply Lp-normalization along the provided axis.
axis: The axis on which to apply normalization, -1 mean last axis. Default value is
p: The order of the normalization, only 1 or 2 are supported. Default value is
input (heterogeneous) - T: Input matrix
output (heterogeneous) - T: Matrix after normalization
T in ( tensor(double), tensor(float), tensor(float16) ): Constrain input and output types to float tensors.