There are a couple of different ways you can collapse your matrix into a vector, depending upon how you want the contents of your matrix to fill that vector. Here are two examples, one using the function reshape (after first transposing the matrix) and one using the colon syntax (:): >> M = [1 2 … Read more
In the following I use terminology that I think is more or less in line with standard Matlab practice. However, in some cases I’ve had to sort-of make up a name because I wasn’t aware of an existing one. Please let me know if there are more standard names than those I’m using. This answer … Read more
Given two tensors A and B you can use either: A * B torch.mul(A, B) A.mul(B) Note: for matrix multiplication, you want to use A @ B which is equivalent to torch.matmul().
Create a 3D matrix A = zeros(20, 10, 3); %# Creates a 20x10x3 matrix Add a 3rd dimension to a matrix B = zeros(4,4); C = zeros(size(B,1), size(B,2), 4); %# New matrix with B’s size, and 3rd dimension of size 4 C(:,:,1) = B; %# Copy the content of B into C’s first set of … Read more
You’re probably going to want four loops – two to iterate over the blocks, and then another two to perform the transpose-copy of a single block. Assuming for simplicity a block size that divides the size of the matrix, something like this I think, although I’d want to draw some pictures on the backs of … Read more