Open 3DTOPO opened 6 years ago
With the original, iterative neural-style, something like this can be achieved by processing the image initially at small size and the feeding the result through the process several times with increasing size.
I guess one could try this with fast-neural-style, too?
Thanks for the suggestion. I have tried that with interesting results, but compared to the low resolution (highly abstract) image, a lot of detail is added which takes away from the more abstract qualities I would like to achieve.
compared to the low resolution (highly abstract) image, a lot of detail is added which takes away from the more abstract qualities I would like to achieve
I know the feeling. I, too, am interested in simpler, abstract-like images. There is a Finnish word I have in mind, "pelkistää" which means "reduce to the bare essentials".
The first convolution layer filter size is 5x5, you can change that to 21x21. Re-trian.
Thanks for the tip. Can that be done with the architecture argument, or does the source code need to be modified?
Yes. In the code:
cmd:option('-arch', 'c9s1-32,d64,d128,R128,R128,R128,R128,R128,u64,u32,c9s1-3')
So you need to use "-arch c21s1-32,d64,d128,R128,R128,R128,R128,R128,u64,u32,c9s1-3" in the training command line.
Thank you very much, I'll give that a try!
But from my experience, you do not want a very high resolution style images. That just give you too much "noise" in the generated image.
Yeah, seems around 256 usually gives the best results for the style image.
-arch c21s1-32,d64,d128,R128,R128,R128,R128,R128,u64,u32,c9s1-3 doesn't work. Any value other than c9s1 seems to generate this error:
bin/luajit: lua/5.1/nn/Module.lua:252: Torch object, table, thread, cdata or function expected stack traceback: [C]: in function 'pointer' lua/5.1/nn/Module.lua:252: in function 'flatten' lua/5.1/nn/Module.lua:326: in function 'getParameters' train.lua:139: in function 'main' train.lua:327: in main chunk [C]: in function 'dofile' .../src/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405d50
Any ideas?
I have found that the all else being equal, the lower the resolution of images to be stylized, the more abstract the image is. For instance, an input image of 256 pixels is significantly more abstract than stylizing the same image at 1024 pixels.
Is there a way to increase the receptive field size by say four-fold, so that at 1024 pixels, the image would be approximately the abstract level of a 256 pixel image, but at a higher resolution?