====== Neural style simulation with tensorflow ======

{{tag>deep_learning}}

I've been away from my blog a bit too long already, but well, the past is the past, and we can't change it. So let's focus on the present and future anyway! Today I wan't to give a try to the so called **"neural style"** concept, where we can input an image, and say a painting with a "given style", and get that style applied on the input image.

====== ======

===== References =====

  * https://www.youtube.com/watch?v=LoePx3QC5Js
  * https://deepart.io
  * https://github.com/hwalsuklee/tensorflow-style-transfer => this is the implementation we will use as reference (it provides links to the original paper)
  * https://github.com/lengstrom/fast-style-transfer

===== Pre-requisite steps =====

  * The first ste we take is to download the reference weights from [[http://www.vlfeat.org/matconvnet/models/imagenet-vgg-verydeep-19.mat|imagenet-vgg-verydeep-19.mat]]
  * Also we need to ensure we have the python packages: **numpy**, **scipy**, **Pillow**, **matplotlib**

===== Initial tests =====

  * So I built a minimal test front end, which can be executed with my custom command: <code>nv_style_transfer --content images/tubingen.jpg --style images/starry-night.jpg --output result.jpg</code>

  * Unfortunately, the first result I got was the exception: <code>    import utils
  File "/mnt/array1/dev/projects/NervSeed/python/apps/deep_learning/style_transfer/utils.py", line 3, in <module>
    import matplotlib.pyplot as plt
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/site-packages/matplotlib/pyplot.py", line 113, in <module>
    _backend_mod, new_figure_manager, draw_if_interactive, _show = pylab_setup()
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/site-packages/matplotlib/backends/__init__.py", line 60, in pylab_setup
    [backend_name], 0)
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/site-packages/matplotlib/backends/backend_tkagg.py", line 6, in <module>
    from six.moves import tkinter as Tk
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/site-packages/six.py", line 92, in __get__
    result = self._resolve()
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/site-packages/six.py", line 115, in _resolve
    return _import_module(self.mod)
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/site-packages/six.py", line 82, in _import_module
    __import__(name)
  File "/mnt/array1/dev/projects/NervSeed/tools/linux/python-3.6/lib/python3.6/tkinter/__init__.py", line 36, in <module>
    import _tkinter # If this fails your Python may not be configured for Tk
ModuleNotFoundError: No module named '_tkinter'</code>

  * Now trying to get this Tk dependency... But, unfortunately, it seems this is something we should build python with.
  * Now trying to see if we can remove this dependency usage... **OK** actually the matplotlib dependency is only used to display the images for debugging, so I simply commented this module import in the **utils.py** file and also the **plot_images** function in that same file. Then the app seems to run as expected and I can see the training process going on. And finally I got my first style transfer result image :-)

{{ blog:2019:0211:first_style_transfer.jpg?512 }}

=> I know I know, that one is pretty standard result ;-) So then I moved to more personal content (ie. family picture) with a custom painting style.

===== Family picture styling =====

  * I first tried with the command: <code>nv_style_transfer --max_size 1920 --content /mnt/array1/dev/data/deep_learning/style_transfer/content/famille_cap_antibes.jpg --style /mnt/array1/dev/data/deep_learning/style_transfer/styles/colorful_sunrise.jpg --output /mnt/array1/dev/data/deep_learning/style_transfer/family_colorful_sunrise.jpg</code>

  * => unfortunately, this didn't work on my dual 1070 config: I run out of **GPU memory**... :-( So it seems generating 1080p images is still a bit out of reach for me... Maybe if I try on my GTX 1080 instead ?

  * So now trying with 720p output images: <code>nv_style_transfer --max_size 1280 --content /mnt/array1/dev/data/deep_learning/style_transfer/content/famille_cap_antibes.jpg --style /mnt/array1/dev/data/deep_learning/style_transfer/styles/colorful_sunrise.jpg --output /mnt/array1/dev/data/deep_learning/style_transfer/family_colorful_sunrise.jpg</code>

  * And the first "custom result" I got didn't look so great:

{{ blog:2019:0211:family_colorful_sunrise_1000.jpg?600 }}

  * Note that the style for that experiment came from the painting below:

{{ blog:2019:0211:colorful_sunrise.jpg?600 }}

  * Not quite a wonderfull success, isn't it ?... Yet, the result above was achieved with only 1000 training iterations, and the loss was still going "largely down" when the training was stopped. So I decided to give it another try, this time with 5000 iterations instead to see if this could help producing a more convincing style transfer image :-)

  * The second result I got with those 5000 iterations was:

{{ blog:2019:0211:family_colorful_sunrise_5000.jpg?600 }}

=> Still not quite an amazing image, but at least some of the small artifacts from the previous rendering were removed...

  * At that point I realized that the training was taking soooo long because... my GPUs were actually busy mining crypto currencies at the same time !!! OOooops... ;-) So, maybe I can in fact produce 1080p images afterall ? Anyway, I decided to stick with 720p resolution and instead try with another painting style, which was the following:

{{ blog:2019:0211:paysage_texture.jpg?600 }}


  * And the result I got (this time with +6000 iterations) was:

{{ blog:2019:0211:family_paysage_texture.jpg?600 }}

=> Again, the result is "nice" but still not really terrific... In fact I'm starting "to feel" that what we really need as a "style" image is not really a "colorfull" painting but instead something with very specific "shapes" instead. So let's try to find that now.

  * I found this abstract painting, which I decided to use:

{{ blog:2019:0211:abstract_painting.jpg?300 }}

  * And the result, with "only" 3000 iterations seems much more convincing to me (even if we still have a few artifacts... But I'm sure this can be fixed with some more training):

{{ blog:2019:0211:family_abstract_painting.jpg?600 }}

/*
nv_style_transfer --max_size 1280 --num_iter 6000 --content /mnt/array1/dev/data/deep_learning/style_transfer/content/famille_cap_antibes.jpg --style /mnt/array1/dev/data/deep_learning/style_transfer/styles/paysage_texture.jpg --output /mnt/array1/dev/data/deep_learning/style_transfer/family_paysage_texture.jpg


nv_style_transfer --max_size 1280 --num_iter 3000 --content /mnt/array1/dev/data/deep_learning/style_transfer/content/famille_cap_antibes.jpg --style /mnt/array1/dev/data/deep_learning/style_transfer/styles/abstract_painting.jpg --output /mnt/array1/dev/data/deep_learning/style_transfer/family_abstract_painting.jpg

nv_style_transfer --max_size 1280 --num_iter 6000 --content /mnt/array1/dev/data/deep_learning/style_transfer/content/chatte.jpg --style /mnt/array1/dev/data/deep_learning/style_transfer/styles/nude_grayscale.jpg --output /mnt/array1/dev/data/deep_learning/style_transfer/chatte_grayscale.jpg

nv_style_transfer --max_size 1280 --num_iter 6000 --content /mnt/array1/dev/data/deep_learning/style_transfer/content/chatte2.jpg --style /mnt/array1/dev/data/deep_learning/style_transfer/styles/cubism.jpg --output /mnt/array1/dev/data/deep_learning/style_transfer/chatte2_cubism.jpg --loss_ratio 0.0007
*/

<note>By the way, I also tried once more to generate a 1080p image [with mining stopped this time!] but unfortunately I still get the same "out of GPU memory" error.</note>

===== Future tests =====

  * As mentioned in the reference section above, there is actually a **fast style transfer** implementation that can apparently produce similar results much faster. I should definitely give this a try one day... But not today ;-).