TFiFiE

One can easily find colors with dubiously large differences between them just by adding a few random bits to #000000, but here are a few examples: |sRGB255 color 1|sRGB255 color...

@njsmith, you never heard back from them? Since CAM16-UCS seems to have the same issue, would it be fair to instead crown Jzazbz as the uniform color space of choice?

In terms of subject matter, [Colour](../../../colour-science/colour) has everything colorspacious has, no? However, I would look into why the color difference is off by almost 0.02 in that example above, as...

OK, I found out the difference is mostly due to you having used `4` instead of `64/pi/5` as the CIECAM02 _L_A_ parameter. On a side note, it raises my eyebrow...

> But an even smaller [change] that deviates from greyscale produces a large change in CAM02-UCS's hue/colorfulness coordinates: This is quite interesting in light of the fact that "hue linearity"...

Maybe it's a bit pedantic, but the color space itself is obviously not invariant with respect to illumination, which is nonsensical. Perhaps something like _Illumination-**Uniform** Colour Space_ would better convey...

@sethtroisi, you might want to update your LeelaChessZero link to: https://github.com/LeelaChessZero/lczero-training/blob/master/tf/tfprocess.py#L645

What if bias is used _instead_ of weighting (gamma)? Can it be confirmed that the presence of the former won't already give the same improvement as having both?