Multicore CPU Support?
Is there any way to optimize training for systems without a GPU?
I'm attempting to train on a system with 8 cores, but no GPU, and I notice it's only using a single core. I didn't expect it to be super efficient without a GPU, but I thought it would at least take advantage of all the cores available.
Punctuator uses Theano and it should support multiple cores to some extent http://deeplearning.net/software/theano/tutorial/multi_cores.html# , but I personally haven't experimented with training on CPU
You can also check if you have better luck using Tensorflow version: https://github.com/cadia-lvl/punctuation-prediction/tree/master/punctuator2tf2