neural-style-docker
neural-style-docker copied to clipboard
albarji
A dockerized version of neural style transfer algorithms
Don't see a reason not to do 2048 for tile size. Might reduce if I run into crashes.
Hello, using the chen-schmidt algoritm I sometimes get the following error Segmentation fault (core dumped) convert: unable to open image `/tmp/tmpf6s38rl5/rgb_stylized.png': No such file or directory @ error/blob.c/OpenBlob/2712. convert: no...
`WARNING:neuralstyle.algorithms:Unknown GPU model NVIDIA Tesla K80, will use default tiling parameters `
Hi @albarji, first of all thank you for creating a dockerized version of the neural-style project! :) However, i'm not able to get it to run properly. I'm calling it...
> Traceback (most recent call last): File "/app/entrypoint/entrypoint.py", line 100, in main styletransfer(contents, styles, savefolder, size, alg, weights, stylescales, tileoverlap, algparams=otherparams) File "/app/entrypoint/neuralstyle/algorithms.py", line 84, in styletransfer if fitsingletile(targetshape(content, size),...
Numpy is used only for the functions linspace and prod, but installing it requires quite a few packages that make the docker image heavier. The project could benefit from replacing...
Hi! I'm an artist and designer (and a sorta crappy dev) who fiddles around with Deep Style in my spare time. I recently have been[ doing a bunch of articles](https://www.jackalope.tech/how-artists-can-set-up-their-own-neural-network-part-2-neural-network-install/)...
It seems that for some images transparent patches appear out of nowhere in chen-schmidt-inverse algorithm.
Try adding the "Universal Style Transfer" method, which promises better results than chen-schmidt at fast speed. * https://github.com/sunshineatnoon/PytorchWCT * https://arxiv.org/pdf/1705.08086.pdf
Following [the remote-launch outline laid out in @albarji's blog post](https://medium.com/devopsion/how-to-fake-it-as-an-artist-with-docker-aws-and-deep-learning-6d42f4acd890) . . . 1. Booting a remote `p2.xlarge` server with Ubuntu 16.04.2 LTS (GNU/Linux 4.4.0-1020-aws x86_64) 2. Cloning the repo...
