Why GANs for this?
Show HN: Colormind – Color schemes via Generative Adversarial Networks
31–40 of 55 posts
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#32If the site gave fascist propaganda posters as an example, how would that fly? Why are communist propaganda posters ok?
They are a distinct art style that the algorithm was able to identify. I don't have a problem with it being used as an example. Why isn't it ok?
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#33If the site gave fascist propaganda posters as an example, how would that fly? Why are communist propaganda posters ok?
It's just showing the results when Mao-era propaganda posters are used as input.
Not sure I understand the concern. I guess "Communist" is a bit broad, but I don't see it as offensive.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#34If the site gave fascist propaganda posters as an example, how would that fly? Why are communist propaganda posters ok?
How are they not ok? Is the color palette used in propaganda eternally tainted in some way? The algorithm distilled the content into a representative palette, nothing more.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#35Why GANs for this?
My question as well. There are several other great implementations of a color pallet generator which use color theory rules. My bet is that the GAN, in this instance, boils down to little more than a pseudorandom number generator.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#36Using deepmind for generating color palettes is somewhat of an overkill. It is really not that hard a problem. It is very easy to programatically generate several color palettes from a main color. It is also wasy to select one or more main colors from a picture.
Good point, just blindly select several "harmonious" colors are not hard at all. But as some folks pointed out, if we want to also consider the context (where the colors will be used, is it a button? or background? or text?), deep learning is definitely a good fit.
Do you have any evidence that ML is a good fit? You seem so sure.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#37Very cool! One thing I noticed is that if you lock all colors except one and press 'generate' repeatedly, each call produces a different color. Why is that?
the model isn't totally deterministic, but aside from that the main palette is actually an ensemble of 12 separate models trained on slightly different hyper-parameters. Colors are kind of subjective, and this is just meant to add some variety. eg. If you make a gradient out of 4 shades of the same color most of the models will complete the gradient, but a few of them would give you a contrasting shade.
> an ensemble of 12 separate models trained on slightly different hyper-parameters
Sounds like a PRNG to me.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#38Why GANs for this?
My question as well. There are several other great implementations of a color pallet generator which use color theory rules. My bet is that the GAN, in this instance, boils down to little more than a pseudorandom number generator.
I think color theory alone isn't enough to produce good color palettes. eg. try going to https://color.adobe.com and choose one of the color rules, then go to https://color.adobe.com/explore and compare with user-contributed palettes. There's a huge difference imo.
As for why a GAN specifically, I talk a bit about that in one of the blog posts. Neural nets trained with L1/L2 loss tend to produce "averaged" colors, dull greys and browns. The learned loss from a GAN allows the output to take on more extreme values.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#39I do love these color scheme generators, and perhaps this is a suggestion for improvement, the color vs. dominance of the color seems very important as well. That is, proportionally showing the palette based on how dominant that color should be in an overall end design
the issue I see is that most sites have a white/beige background, which could get repetitive for the purposes of design inspiration. Maybe train a separate model for bootstrap/direct insertion.
Re: Show HN: Colormind – Color schemes via Generative Adversarial Networks
#40This looks great! Did you have any thoughts with regards to releasing it as open source so that we could run our own instances with the various training sets? I note that you appear not to be monetizing it at all, so I figured I'd pop the question :)
the GAN is actually just pix2pix: https://github.com/phillipi/pix2pix
I just resized the convolutional layers to 1px height since the vertical dimension isn't that relevant in this case.
I do have a few bash scripts for color extraction that I could upload to github, although they're pretty quick and dirty.