com.microsoft - QLinearReduceMean#

QLinearReduceMean - 1#

Version

  • name: QLinearReduceMean (GitHub)

  • domain: com.microsoft

  • since_version: 1

  • function:

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 1 of domain com.microsoft.

Summary

Attributes

  • axes - INTS (required) : A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor.

  • keepdims - INT (required) : Keep the reduced dimension or not, default 1 mean keep reduced dimension.

Inputs

Between 4 and 5 inputs.

  • data (heterogeneous) - T:

  • data_scale (heterogeneous) - tensor(float):

  • data_zero_point (optional, heterogeneous) - T:

  • reduced_scale (heterogeneous) - tensor(float):

  • reduced_zero_point (optional, heterogeneous) - T:

Outputs

  • reduced (heterogeneous) - T:

Type Constraints

  • T in ( tensor(int8), tensor(uint8) ): Constrain input types to 8 bit signed and unsigned tensors.

Examples