Closed Liangmp closed 5 years ago
Huh it shouldn't be that slow unless you're running it on a huge image. See #20
Also, using a GPU will make it a lot faster.
Thank you for your reply. I will try it again with a smaller image and see if it works.
As a test, try a really small image, e.g. 128x128: you should be able to see it work, and you can scale up from there.
That helps a lot! It works now.
I typed the command in terminal: python neural_style.py --content 1-content.jpg --styles 1-style.jpg --output test2.jpg --iterations 10
And I got a this warning: /anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from
float
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
. from ._conv import register_converters as _register_convertersEven though I set --iterations as a very small number like 10, it still takes me a very long time (like hours) without outputting anything.
Could you help me point it out if there is something wrong?