Closed mtewes closed 7 years ago
Nice. The fact that the colours become lighter with iteration means that the differences between the samples increase?
No, alpha and lightness do not change here. It's just that subtle differences between cases become visible only after a bit of training.
okay!
In a more realistic case:
Issues with this
It's interesting to see and understand this plot, but maybe this is not a top priority.
Done with the plot -- it is activated by a kwarg to the training constructor. Will now find a solution to pass it as option from MegaLUT.
Note that the problem (above) with the many iterations is now fixed. We only save some snapshots.
:+1:
Done and merged.
Status report: