George Stoyanov

Hi guys, I'm currently experiencing Out of memory exceptions. I use your library to blur single images in separate activities, but it seems that on lower-end devices this causes out...

what fixed it for me was: 1. uninstall torch 2. `sudo apt-get install libjpeg-dev libpng12-dev` I'm running Ubuntu 14.04, you might have to find the appropriate "lib" packages for your...

> I would be interested in seeing if any changes need to be made to make MS SQL work. I've managed to get it to login using a connection string...

hi @gaogao22, what do you mean by theories? Are you interested in other applications of this architecture or mainly explanations why it might work better than other models?

In which file are you receiving the error? Did you use the requirements file to install all dependencies?

yes, initially I thought that something with the generation didn't go good - since this script never completed: `python generate.py --n_jobs 30 --n_colors 4 --style_image data/starry/style.png --style_mask data/starry/style_mask.png --out_hdf5 data/starry/gen_doodles.hdf5...

thanks, I'll try that! How much time does it take on ur setup? Do you advise to increase the jobs? I'm using a Tesla K10 setup

I managed to get it working, unfortunately it looks like the VRAM (3.5GB) is not enough. What's the best way to reduce the memory footprint? p.s.: I'm familiar with Johnson's...

looks like batch_size=1 did the trick, I previously tried with 2 and 3 with no success. Does this affect the quality or just the speed of the training?

BTW, do you recommend this repo for artistic neural transfer? probably to do it well there should be some semantic analysis that determines the masks :? Is there any other...