Concat Backward Layer

The forward concat layer generates a tensor from input arguments X . For more details, see Forward Concat Layer. The backward concat layer deconcatenates a tensor from the input argument G into multiple output tensors Z (j).

Problem Statement

Given the dimension k along which the concatenation to be implemented, a collection N = (n k 1 ,..., n k t ) of t integer elements, and a p-dimensional tensor G =(g i 1...i p ) of size n 1 x n 2 x ... x n p , the problem is to generate t p-dimensional tensors Z (j), j=1, ..., t, of size n 1 x... n k j x ... x n p such that:

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)