Scaler#

Domain: ai.onnx.ml
Since version: 1

Rescale input data, for example to standardize features by removing the mean and scaling to unit variance.

Inputs

X (T): Data to be scaled.

Outputs

Y (tensor(float)): Scaled output data.

Type Constraints

T: The input must be a tensor of a numeric type. Allowed types: tensor(double), tensor(float), tensor(int32), tensor(int64).

Examples#

test_cc_scaler_float

Node:
  ai.onnx.ml.Scaler(x) -> (y)
  Attributes:
    offset = [0.5, 1.0, 1.5]
    scale = [2.0, 0.5, 1.0]

Inputs:
  x: shape=(2, 3), dtype=float32
    [[0., 1., 2.],
     [3., 4., 5.]]

Outputs:
  y: shape=(2, 3), dtype=float32
    [[-1. ,  0. ,  0.5],
     [ 5. ,  1.5,  3.5]]

test_cc_scaler_int64

Node:
  ai.onnx.ml.Scaler(x) -> (y)
  Attributes:
    offset = [1.0]
    scale = [0.5]

Inputs:
  x: shape=(5,), dtype=int64
    [0, 1, 2, 3, 4]

Outputs:
  y: shape=(5,), dtype=float32
    [-0.5,  0. ,  0.5,  1. ,  1.5]