Way to run operations on CPU, thusly RAM instead of GPU/VRAM?

[mxchinegod]

I'm limited by the Amazon instance. I can buy a server with a K80 and 12GB of VRAM but I'd also be willing to pay more for slower processing on the cloud if I can get the CPU working.

I'm going to look at the code after this but in the event that the answer is obvious to the community, I wanted to ask before I go digging.

Thanks so much! Hope everyone's results have been fun.

[FabienLavocat]

Just do not enable CUDNN and the script will run on a CPU. But it will take you hours if not days to get a picture.

[andersbll]

The CPU implementation of the convolution operation is too slow for any practical use. You would have to implement something faster first.

[mxchinegod]

I believe you that it's slow and I appreciate both very quick responses!

Since our needs may be slightly different, by what magnitude is it impractical? We talking days or weeks for 1MP + resolution?

Thanks!

[johndpope]

fyi https://github.com/jcjohnson/neural-style/

[mxchinegod]

I've used it, the results even with gradient smoothing are not ideal whatsoever. I've done enormous amounts of tweaking and attempted to isolate what I like about it, it just isn't as good. I will perhaps come back to it anyways because it's more fleshed out.