ai.onnx.ml - Imputer#

Imputer - 1#

Version

  • name: Imputer (GitHub)

  • domain: ai.onnx.ml

  • since_version: 1

  • function:

  • support_level: SupportType.COMMON

  • shape inference: False

This version of the operator has been available since version 1 of domain ai.onnx.ml.

Summary

Attributes

  • imputed_value_floats - FLOATS : Value(s) to change to

  • imputed_value_int64s - INTS : Value(s) to change to.

  • replaced_value_float - FLOAT : A value that needs replacing.

  • replaced_value_int64 - INT : A value that needs replacing.

Inputs

  • X (heterogeneous) - T:

Outputs

  • Y (heterogeneous) - T:

Type Constraints

  • T in ( tensor(double), tensor(float), tensor(int32), tensor(int64) ): The input type must be a tensor of a numeric type, either [N,C] or [C]. The output type will be of the same tensor type and shape.

Examples