artnose

Ok, that makes sense... Would pre-cropping all the training images speed things up at all? It's taking me 2 days to run a training set on my old graphics card....

Man I wish I could get this compiled. I can't get the SDK or this with all the dependencies. What's the compile command for this? For the SDK, gives me...

How does it transfer arbitrary style? That's not a modification on this project is it?

Is there a solution to this? Downgrade chainer or upgrade the code?

That would be awesome, but I'm getting an error.. `Traceback (most recent call last): File "generate.py", line 55, in med = original_colors(original, med) File "generate.py", line 27, in original_colors return...

Hmm, so, input image was 800x531 and output image is 800x528 with out --keep_colors so, it's cropping it and then the color merge doesn't work

It's a pretty good result. I don't think you'll get better with out more training images... but I'm just learning this as well. For the patterns, they could be fixed...

I'd like to know this too.

On the same system, is the Torch implementation or this implementation faster? better? Anyone have comparisons?