Using a RNN that makes up plausible names based on a training set of actual colors.
I kinda hope that was a genuinely curious question and not an arrogant rhetoric one.
I kinda hope that was a genuinely curious question and not an arrogant rhetoric one.
for something like a meaningful name for a colour requires far more learning, data and context than is reasonable...
_, result = min([(sqrt((i.R - c.R)^2 + (i.G - c.R)^2 + (i.B - c.B)^2), c) for c in colors])
Why would you want a computer to come up with color names anyway? They're identifiers, so you want them to be consistent. What if it comes up with names like Piss or Ennui? Why go through that trouble?