Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

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.



Why RNN? I would probably settle for a nearest neighbour in Lab color space.


Because I'm no data scientist but I somewhat understand that a RNN can extrapolate a training set. Nearest neighbors are cool too!


your conception of RNN as a magic bullet is sorely mistaken.

for something like a meaningful name for a colour requires far more learning, data and context than is reasonable...


Welp


You've got like 3 features, and a list of names with values for each one of those features. You could literally do

    _, result = min([(sqrt((i.R - c.R)^2 + (i.G - c.R)^2 + (i.B - c.B)^2), c) for c in colors])
and you're done.

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?


You can skip the square root, too.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: