Loading TOC...

cntk:uniform-random-like

cntk:uniform-random-like(
   $x as cntk:variable,
   [$low as xs:double],
   [$high as xs:double],
   [$seed as xs:unsignedLong],
   [$name as xs:string]
) as cntk:function

Summary

Create an instance of a uniform random operation. This produces random numbers with the shape and dynamic axes specified by the operand, uniformly distributed in [low, high)

Parameters
$x Cntk variable (input, output, parameter, or constant) from which to copy the shape, data type, and dynamic axes.
$low Lower end of the range of the random numbers.
$high Upper end of the range of the random numbers.
$seed Pseudo random number generator seed (default: automatically select a unique seed)
$name The name of the function instance in the network.

Example

  let $input-variable1 := cntk:input-variable(cntk:shape((3)), "float",
    fn:false(), fn:false(), "feature")
  return cntk:uniform-random-like($input-variable1, -6219606133.877441,
    5146702661.592827, 10739236701558670986, "Ekst~zfU")
  => cntk:function(Composite RandomDistribution (Input(Name(feature), Shape([3]),
  Dynamic Axes([Sequence Axis(Default Dynamic Axis), Batch Axis(Default Batch Axis)]))))

Stack Overflow iconStack Overflow: Get the most useful answers to questions from the MarkLogic community, or ask your own question.