-
Notifications
You must be signed in to change notification settings - Fork 6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
sin_colors extraction #7
Comments
Maybe we could use different color extractors. |
Concur, but suggestions approaching this problem there as well? Repeat colors with highest frequency maybe? An alternative would be to figure a way to dynamically do node count, but it would probably be more work. |
@jmbi wrote the go color extracter, maybe he could take a look at that as he has already done his study on the subject. |
I have, the issue is still present there(not a fault of the program), only there's no option to print up to a specified number to extract. This makes sense in situations where there aren't x amount of colors to pull (targeting ten as that's the node number we've been associating). My test input was this image from subtle patterns. |
OK, when the
This happens and less than 10 colors are returned. Namely
At the moment it's just doing some shell script magic. |
I'm acting under the assumption we want to get to ten colors to use as
training input:
If there aren't ten colors to pull, my thought was we could fill up to ten
colors with an average of the existing colors.
ie if for some reason we only pulled 2 colors from a picture, `ffffff` and
`000000`, colors 3-10 could be `cccccc`.
|
Or we could use a random chosen color from the set. We can test out the two options, that will need re-extracting the colors from the whole dataset. |
True, the average colors thing was an attempt to negate favoring one color
Yeppyepp, this would have needed to happen anyway (In the current set, Pretty sure we're on the same page about options here now, will proceed On Thu, May 19, 2016 at 10:32 AM, Patrick Louis notifications@github.com
Nathan Isom |
In the spirit of this issue: #7 (comment) This is still an ongoing test.
https://github.com/nixers-projects/urnn/blob/master/urnn#L78 and Maybe we should write a simple script that handles that. Takes colors and output 10 colors from them considering all the edge cases. |
I updated I'm thinking that this doesn't make any sense if the colors aren't "ordered" in some way. What do you think? |
I concur, but as opposed to picking random colors I would prefer to fill Thanks, On Wed, Jun 1, 2016 at 3:25 AM, Patrick Louis notifications@github.com
|
I'm not that good with color theory. |
I was just thinking mathematical average (There's probably a better color So say we had a picture with 3 colors pulled: #000000 These equate to: RGB 0, 0, 0 So, we can average with: R = (0 + 0.078 + 1)/3 = 0.36 * 255 = 5C so the average of the colors is #5C635C. Thanks, On Wed, Jun 1, 2016 at 11:32 PM, Patrick Louis notifications@github.com
|
Yeah, this doesn't seem very accurate but we can try. Let's see what some sample colors will have as complementary colors. |
Leaving a link here for reference later: My goal with this is to neutralize any input beyond limited colors that may Thanks, On Tue, Jun 21, 2016 at 3:51 PM, Patrick Louis notifications@github.com
|
This seems very promising. This is what we're gonna try implementing. |
I committed some scripts to convert from one color space to another. |
Yes, my impression was we would mix the colors pulled, and then use the result of that mixing for the rest of the empty slots (not continually mix) |
I don't get it, you want to mix 5 colors together if we only have 5 colors. |
In that example, we would mix the five colors. And then, use the result of that mixing as the value for the other five colors (give them all the same value). |
It's nice to fill the missing colors but the neural network presupposes that the inputs are always in the same order, from darker to lighter. |
I was also thinking, maybe we can feed the neural network Lab colors instead of RGB colors. |
I wrote a script called The scripts to convert from one colorspace to another could be used to feed the network Lab colors instead of RGB but then we'll have to recalibrate the ranges so that we can map Lab to [-1,1]. |
Currently when colors are extracted, if ten aren't found, we fill in the gap up to ten with #000000. This results in a skewed association with dark colors
The text was updated successfully, but these errors were encountered: