Loading TOC...

cntk:eye-like

cntk:eye-like(
   $x as cntk:variable,
   $is-output-sparse as xs:boolean,
   $name as xs:string
) as cntk:function

Summary

Create an instance of a eye-like operation. This produces ones with the shape and dynamic axes specified by the operand.

Parameters
$x Numpy array or any Function that outputs a tensor of rank 2.
$is-output-sparse Whether the output is sparse or not.
$name The name of the function instance in the network.

Example

  let $input-variable1 := cntk:input-variable(cntk:shape((3,4)), "float",
    fn:false(), fn:false(), "feature",())
  return cntk:eye-like($input-variable1,fn:false())
  => cntk:function(Composite EyeLikeOp (Input(Name(feature), Shape([3 x 4]),
  Dynamic Axes([]))))

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