divideint uses a deterministic algorithm to partition the indices. You can use dividerand instead for a random partition of indices.
If you’re working with image/audio datastores, you can also use the splitEachLabel function. The documentation page has good examples.
If you’d like to do it without any existing function, you can do it as follows. This is similar to how it’s done in the YOLOv2 Object Detection example:
shuffledIndices = randperm(N);
idx = floor(0.6 * length(shuffledIndices) );
trainingIdx = 1:idx;
validationIdx = idx+1 : idx + 1 + floor(0.1 * length(shuffledIndices) );
testIdx = validationIdx(end)+1 : length(shuffledIndices);
