VisualApplets
Operator Reference

Operator Library: Base

With the CastKernel operator, you can re-organize the parallelism and kernel size of the incoming data. For re-interpretation, change the kernel size at the output link. For example, an input link is configured with two kernel rows and two kernel columns and a parallelism of four. The CastKernel operator gives you the possibility to interpret these as four kernel rows and four kernel columns at parallelism 1 or as one kernel row and two kernel columns at parallelism 8, etc. The constraint of the CastKernel operator is that the product of kernel row and kernel column and parallelism must be identical for the input and the output link.

The following examples illustrate the conversion of kernel configuration and parallelism performed by the operator. The pseudo-code below the illustrations also describes the conversion pattern.

Example 1: Converting the kernel size (col x row) 3x1 to the kernel size 1x3 while keeping parallelism 2:

Example 2: Converting parallelism 2 and kernel size (col x row) 2x3 to parallelism 3 and kernel size 2x2:

Example 3: Converting parallelism 1 and kernel size (col x row) 3x2 to parallelism 6 and kernel size 1x1:

The operator changes the width of the images.

The mapping follows the following pseudo-code:

        
        pi = 0
        ri = 0
        ci = 0
        for p in 0 to P-1
          for r in 0 to R-1
            for c in 0 to C-1
              O[p][r][c] = I[pi][ri][ci]
              ci = ci + 1
              if ci >= Ci then ci = 0, ri = ri + 1
              if ri >= Ri then ri = 0, pi = pi + 1
        
      

The pseudo-code has the following meaning:

The function of the CastKernel operator could also be achieved by combining the follwoing operators: SplitKernel, MergeKernel, SplitParallel and MergeParallel:

In this example, the input configuration of four kernel columns and two kernel rows at parallelism 3 is re-organised to two kernel columns and three kernel rows at parallelism 4. The same can be achieved with the operator CastKernel by configuring the output link respectively: