Reproducibility convolutional neural network training with gpu
7 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Diego Alvarez Estevez
el 20 de Sept. de 2018
Comentada: Mesho
el 24 de Mayo de 2024
Hello,
I am training a CNN using my local GPU (to speed up training) for classification problems and would like to try different parameterizations. To avoid the variability effects due to different data and/or weights initialization I am resetting the random seeds each time before training:
% Initialize random seed (thus same dataset on same architecture would lead
% to predictable result)
rng(0);
%parallel.gpu.rng(0, 'CombRecursive');
randStream = parallel.gpu.RandStream('CombRecursive', 'Seed', 0);
parallel.gpu.RandStream.setGlobalStream(randStream);
% Train the CNN network
net = trainNetwork(TR.data,TR.reference,layers,options);
The problem is that when using GPU I am getting different results on each execution, even if initializing the GPU random seed to the same value. Strange thing is if I use CPU instead, then I do get the reproducible results. I am doing something wrong with GPU random seed initialization? Is there a know problem for this situation or something I am missing?
Thanks beforehand.
PS: I am using Matlab R2017b
0 comentarios
Respuesta aceptada
Joss Knight
el 20 de Sept. de 2018
Use of the GPU has non-deterministic behaviour. You cannot guarantee identical results when training your network, because it depends on the whims of floating point precision and parallel computations of the form (a + b) + c ~= a + (b + c).
Most of our GPU algorithms are in fact deterministic but a few are not, for instance, backward convolution.
14 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Parallel and Cloud en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!