Loading TOC...

cntk:depth-to-space

cntk:depth-to-space(
   $operand as cntk:variable,
   $block-size as xs:unsignedLong,
   $name as xs:string
) as cntk:function

Summary

Rearranges elements in the input tensor from the depth dimension into spatial blocks. This operation is useful for implementing sub-pixel convolution that is part of models for image super-resolution (see [1]). It rearranges elements of an input tensor of shape (Cxbxb, H, W) to a tensor of shape (C, bxH, bxW), where b is the block_size.

Parameters
$operand Input tensor.
$block-size Integer value. This defines the size of the spatial block where the depth elements move to. Number of channels, C, in the input tensor must be divisible by math:(block_size times block_size)
$name The name of the function instance in the network.

Example

  let $input-variable1 := cntk:input-variable(cntk:shape((2,3,4)), "float",
    fn:false(), fn:false(), "feature",())
  return cntk:depth-to-space($input-variable1,2)
  => cntk:function(Composite DepthToSpace (Input(Name(feature),
  Shape([2 x 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.