MATLAB: Training NN with single precision data on GPU

deep learningfitnetgpusingle precision data

I am trying to use fitnet to train a network on my GPU using single-precision input data (X and T). However, this always returns an error, which starts with:
"Error using nnGPUOp.bg (line 134) Variable 'perfs1' changed type. Consider renaming variable on left hand side of assignment."
This only seems to be a problem when using single-precision data AND the GPU. When I train using double-precision on GPU, it works fine, and when I use single- or double-precision data on the CPU, it also works fine.
Anyone found a way around this?

Best Answer

Hi,
The single precision GPU training can only be done in the ‘nnGPU’ calculation mode. By default train uses ‘nnGPUOp’ which doesn’t support single precision GPU Training.
As a workaround, you may do single precision GPU training by any of the two ways mentioned below:
  • You can use the nndata2gpu function: 
% Here x,t are original double precision data 
net = configure(net,x,t); 
sx = nndata2gpu(x,'single'); 
st = nndata2gpu(t,'single'); 
[net,tr] = train(net,sx,st,'useGPU','yes');
  • You can specify single precision GPU training: 
 % Here x,t are single precision data 
[net,tr] = train(net,x,t,nnGPU('precision','single'));
Hope it helps.
Related Question