Round#

  • Domain: ai.onnx

  • Since version: 22

Round takes one input Tensor and rounds the values, element-wise, meaning it finds the nearest integer for each value. In case of halves, the rule is to round them to the nearest even integer. If input x is integral, +0, -0, NaN, or infinite, x itself is returned. The output tensor has the same shape and type as the input.

Examples:

round([0.9]) = [1.0]
round([2.5]) = [2.0]
round([2.3]) = [2.0]
round([1.5]) = [2.0]
round([-4.5]) = [-4.0]

Inputs

  • X (T): Input tensor

Outputs

  • Y (T): Output tensor

Type Constraints

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

Examples#

test_cc_round

Node:
  Round(x) -> (y)

Inputs:
  x: shape=(2, 3), dtype=float32
    [[ 0.9,  2.5,  2.3],
     [ 1.5, -4.5, -2.5]]

Outputs:
  y: shape=(2, 3), dtype=float32
    [[ 1.,  2.,  2.],
     [ 2., -4., -2.]]

test_round

Node:
  Round(x) -> (y)

Inputs:
  x: shape=(15,), dtype=float32
    [ 0.1,  0.5,  0.9,  1.2,  1.5,  1.8,  2.3,  2.5,  2.7, -1.1, -1.5, -1.9, -2.2,
     -2.5, -2.8]

Outputs:
  y: shape=(15,), dtype=float32
    [ 0.,  0.,  1.,  1.,  2.,  2.,  2.,  2.,  3., -1., -2., -2., -2., -2., -3.]

Differences with previous version (11)#

SchemaDiff: Round (domain 'ai.onnx')

  • old version: 11

  • new version: 22

  • breaking: no

Type constraints:

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

Version History#