[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vp / vr / w / wg / wsg / wsr / x / y ] [Home]
4chanarchives logo
neural style for windows?
Images are sometimes not shown due to bandwidth/network limitations. Refreshing the page usually helps.

You are currently reading a thread in /wsr/ - Worksafe Requests

Thread replies: 8
Thread images: 1
File: 55e542e667f2c.jpg (127 KB, 929x686) Image search: [Google]
55e542e667f2c.jpg
127 KB, 929x686
I was using this website (neural.0101010101.com) to make neural style images, but it's been down for a couple weeks.. probably too much traffic and porn. Is there any alternatives for a windows 64bit laptop?
>>
>>116290
https://archive.nyafuu.org/wsr/thread/111118/
>>>/gd/267652
>>
>>116303
>112227 here
I worked for a couple of days on trying to get the neural_artistic_style module to function, and made some slight progress, but never fully completed it. Error codes returned make me think my PC lacks sufficient memory to process the style; I have more RAM and a bigger GPU in the mail, so I'll be trying again soon.
As far as my progress, I did discover a few things:
1) Apparently cudarray hasn't been optimized or updated to work with Python 3.5 yet, so anyone attempting to use it on Windows needs to download Python 2.7 instead. This allowed me to install all of the listed prerequisite modules (deeppy, cudarray, scipy, numpy).
2) The modules need a specific release of numpy (Numpy+MKL), as listed here: http://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy
I utilized numpy-1.11.0+mkl-cp27-cp27m-win32.whl, and it seemed to process fine.
3) I do not have access to cuDNN, one of the listed requirements for the neural_artistic_style module. I attempted to run it anyway, and was simply greeted with a memory error.
>>
>>116303
thanks for the linky ;]

>>116317
>python, deeppy, cudarray, scipy, numpy
all that gibberish is why i used the website instead.. ;(
>>
>>116403
Those are all just the names of modules needed to run the neural_artistic_style.
I realize simply listed out like that, they do look like gibberish; my initial goal was to attempt to get the module working so I could write up a step - by - step guide for those less savvy/willing to slog through the trial and error.
I only listed them here so that maybe someone more savvy than myself (with better memory specs) could possibly try without having to do the same mucking about I did.
Any luck with the provided links?
>>
>>116477
Can''t you just use pip to install every library you need?
>>
>>116477
DreamScope is probably the second best online option, lots of filters to choose from, but the finished product leaves a lot to be desired..
>>
>>116479
>>116479
pip worked with most of the needed libraries, but apparently doesn't recognize the cudarray module at all. I only ever got it to install using the setup.py.

Not that it seems to matter now, though; it looks like the program has exploded all over the place.
https://www.instapainting.com/ai-painter
Thread replies: 8
Thread images: 1

banner
banner
[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vp / vr / w / wg / wsg / wsr / x / y] [Home]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
If a post contains personal/copyrighted/illegal content you can contact me at [email protected] with that post and thread number and it will be removed as soon as possible.
DMCA Content Takedown via dmca.com
All images are hosted on imgur.com, send takedown notices to them.
This is a 4chan archive - all of the content originated from them. If you need IP information for a Poster - you need to contact them. This website shows only archived content.