How to do real time processing about chainer-fast-neuralstyle HOT 9 OPEN

How much time does it takes to process one frame at given resolution with your machine ?

from chainer-fast-neuralstyle.

See here: https://github.com/genekogan/CubistMirror

from chainer-fast-neuralstyle.

@ttoinou

I use command
$ python generate.py sample_images/image0001.jpg -m models/composition.model -o sample_images/output-0001.jpg

/usr/lib/python2.7/dist-packages/pkg_resources.py:1031: UserWarning: /home/gtx1080/.python-eggs is writable by group/others and vulnerable to attack when used with get_resource_filename. Consider a more secure location (set with .set_extraction_path or the PYTHON_EGG_CACHE environment variable).
warnings.warn(msg, UserWarning)

3.45500588417 sec
$

cost 3.455sec

from chainer-fast-neuralstyle.

@6o6o
I try now, thanks

from chainer-fast-neuralstyle.

@sukerlove , hmm, 3.4sec, what the size of your image(image0001.jpg)?

from chainer-fast-neuralstyle.

@xpeng image0001.jpg:640*360

from chainer-fast-neuralstyle.

@sukerlove
Missing -g or --gpu option？

from chainer-fast-neuralstyle.

@kaca0083 @xpeng On GTX 1080 and 1024px image, I am getting response time of ~ 2.5 seconds.
TitanX is reportedly doing it in <1 second. Shouldn't the response time in GTX 1080 be comparable, maybe 1.5sec (max).

from chainer-fast-neuralstyle.

@vermapratyush you may run second time. The first run cost longer time.

from chainer-fast-neuralstyle.