Color training costs based on label value

Open danijar opened this issue 10 years ago • 4 comments

Need to map label space from 0 to 1.

Dec 19 '15 12:12 danijar

Can you describe more?

Dec 28 '16 20:12 greninja

Sure. The idea is to plot the loss for each class as separate lines in the loss diagram. This requires to select colors for the classes. Mapping the possible labels between 0 and 1 would allow to color those lines from a Matplotlib color map. However, now I think hard coding colors from a palette (colorbrewer2.org) is better.

Dec 28 '16 21:12 danijar

I did not understand what exactly is meant by 'class' here? Is it the different methods to train the NN given in gradient.py?

Jan 02 '17 20:01 greninja

Haha I see. By classes I mean the possible labels in a classification dataset.

Jan 06 '17 11:01 danijar