1

i'm new to deep learning and i was using matlab's deep learning toolbox. i wanted to run : "test_example_SAE.m" which builds a stacked auto-encoder and trains and tests it using MNIST dataset, but i couldn't because of this error : *

Error using horzcat
Out of memory. Type HELP MEMORY for your options.

* how much memory does this job want ? i mean can i run deep learning toolbox codes on an average PC with 4GB RAM ? or should i learn to run the code on GPU ?

Mahdi k
  • 25
  • 3

1 Answers1

0

It happened to me as well. If you can decrease number of samples.

Also if you are running 'for' loops, try change it to vectors.

One more hint is to divide your data in pieces(if it's possible) and try to run piece-by-piece.

Those are just my suggestions. No difference if you'll run it on GPU.

You can also try use cluster computing if it is available at your job or university.

Mykola Servetnyk
  • 172
  • 10