ImageNette/Woof Leaderboards - guidelines for proving new high scores?

[grankin (Mikhail Grankin)]

@LessW2020

1 - I would vote we go with whatever works best re; [c_in,32,64,64].
That’s the whole goal of Fastai right, what works best is what we use? The problem of course is now that would disrupt all the baselines for the LB, though at this point it seems the LB is off anyway due to the GPU issue.

More parameters = more FLOPS. It may work worse given same FLOPS budget.

@LessW2020

2 - Side note but the name Over9000 is highly confusing to me. Since Over9000, it’s Ranger+Lars, can we refer to it as RangerLars or Ranger2 or something? That ways it is clearer what it is?

(@grankin - this is your decision since you added Lars in I’d like to update my article to promote your improvement since this is achieving the best scores for 5 epochs, and I think RangerLars or Ranger2 or even RangerPlus is much clearer for people).

It wasn’t really my idea to combine all three improvements. It’s Federico Andres Lois (x.com) suggested that. He combined LARS with RAdam before and named his hybrid Ralamb. Please, give all credit in your article to him. I don’t mind changing name if you think that will make things less confusing.