RandomNormal#

RandomNormal - 1#

Version

  • name: RandomNormal (GitHub)

  • domain: main

  • since_version: 1

  • function:

  • support_level: SupportType.COMMON

  • shape inference: True

This version of the operator has been available since version 1.

Summary

Attributes

  • dtype - INT : The data type for the elements of the output tensor. Default is TensorProto::FLOAT.

  • mean - FLOAT : The mean of the normal distribution.

  • scale - FLOAT : The standard deviation of the normal distribution.

  • seed - FLOAT : (Optional) Seed to the random generator, if not specified we will auto generate one.

  • shape - INTS (required) : The shape of the output tensor.

Outputs

  • output (heterogeneous) - T:

Type Constraints

  • T in ( tensor(double), tensor(float), tensor(float16) ): Constrain output types to float tensors.

Examples