RandomNormal#

  • Domain: ai.onnx

  • Since version: 22

Generate a tensor with random values drawn from a normal distribution. The shape of the tensor is specified by the shape argument and the parameter of the normal distribution specified by mean and scale.

The data type is specified by the ‘dtype’ argument. The ‘dtype’ argument must be one of the data types specified in the ‘DataType’ enum field in the TensorProto message.

Outputs

  • output (T): Output tensor of random values drawn from normal distribution

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 (int[]): The shape of the output tensor.

Type Constraints

  • T: Constrain output types to float tensors. Allowed types: tensor(bfloat16), tensor(double), tensor(float), tensor(float16).

Examples#

test_cc_randomnormal

Node:
  RandomNormal() -> (y)
  Attributes:
    shape = [2, 3]

Inputs:

Outputs:
  y: shape=(2, 3), dtype=float32
    [[ 0.04646347,  1.3829458 ,  0.1371488 ],
     [-1.691909  ,  0.6007101 ,  0.24345492]]

test_cc_randomnormal_double

Node:
  RandomNormal() -> (y)
  Attributes:
    dtype = 11
    shape = [2, 3]

Inputs:

Outputs:
  y: shape=(2, 3), dtype=float64
    [[ 0.04646347,  1.38294577,  0.1371488 ],
     [-1.69190901,  0.60071012,  0.24345492]]

test_cc_randomnormal_seeded

Node:
  RandomNormal() -> (y)
  Attributes:
    mean = 1.0
    scale = 2.0
    seed = 42.0
    shape = [2, 3]

Inputs:

Outputs:
  y: shape=(2, 3), dtype=float32
    [[-7.8826690e-01,  6.6930413e-02,  4.1850791e+00],
     [-2.7278478e+00,  2.0848513e-03,  4.0150185e+00]]

Differences with previous version (1)#

SchemaDiff: RandomNormal (domain 'ai.onnx')

  • old version: 1

  • new version: 22

  • breaking: no

Type constraints:

  • changed ‘T’: added types: [‘tensor(bfloat16)’]

Version History#