divideint divides the same way every time even when I place 'rng shuffle' before it.
3 views (last 30 days)
Show older comments
Brent McWatters
on 21 Jul 2020
Answered: Asvin Kumar
on 6 Aug 2020
Hi,
Code below returns the indices for each of those sets of data but the indices are always the same. How do I set it up so they are different each time?
Thank you,
Brent
rng shuffle;
[trainT,valT,testT] = divideint(nn_config.UnCleanLength,CONFIG.dataSplit.trainingFraction,CONFIG.dataSplit.validationFraction,CONFIG.dataSplit.testFraction);
0 Comments
Accepted Answer
Asvin Kumar
on 6 Aug 2020
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);
0 Comments
More Answers (0)
See Also
Categories
Find more on Define Shallow Neural Network Architectures in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!