ai.onnx.ml - Scaler#
name: Scaler (GitHub)
shape inference: False
This version of the operator has been available since version 1 of domain ai.onnx.ml.
Rescale input data, for example to standardize features by removing the mean and scaling to unit variance.
offset: First, offset by this.<br>Can be length of features in an [N,F] tensor or length 1, in which case it applies to all features, regardless of dimension count.
scale: Second, multiply by this.<br>Can be length of features in an [N,F] tensor or length 1, in which case it applies to all features, regardless of dimension count.<br>Must be same length as ‘offset’
X (heterogeneous) - T: Data to be scaled.
Y (heterogeneous) - tensor(float): Scaled output data.
T in ( tensor(double), tensor(float), tensor(int32), tensor(int64) ): The input must be a tensor of a numeric type.