Closed working12 closed 2 years ago
Hey, did you understand this?
Permutation in matrix is about exchanging rows or columns. Glow generalizes this idea to manipulate tensor along channel dimension without changing its size. Generally, this operation is not exchanging rows or columns but fusing all to one multiple times(e.g., #output channels).
Hi, In the paper there is a line saying "Note that a 1 × 1 convolution with equal number of input and output channels is a generalization of a permutation operation."
I don't understand how this is the case? Can anybody explain or show me things so that I can understand this?