Menshykov

Got 5.8% error with 40|1 on CIFAR-10 for which you've published 6.85%. With a sort of inexactly mean and std adjusted data. Going to try to run it without any...

Okay, so it looks as though adjusting the mean and std (per dataset taking info from training set) actually helps. So the numbers should be even better than the ones...

Ran another test and got 5.9% with 40|1 on that inexactly mean and std adjusted data. And I'm getting 6.1-6.3% on [0..1] data.

I wonder how to make your code work in the cudaHalf space.

5.3% 82-1 1.2m params 4.9% 160-1 2.4m params on that test.

Well, the numbers may depend on an init and hyperparams, like LR scheduling, which is quite different. And possibly also on data preprocessing. I will be testing to see if...

After rerunning the tests you might want to contact the many paper authors that quoted you with those results. Including http://arxiv.org/pdf/1608.06993v1.pdf Interestingly, I guess you might get even more paper...

Also tested with adjusting std, but not mean and it gave about the same result as [0..1]. IMHO, fact that adjusting the mean actually helps, not hurts, amazes me. Counting...

I have an idea as to how that can probably be fixed. Somebody already did something like that some time in the past http://arxiv.org/pdf/1606.02228v2.pdf -> image preprocessing mini network. Gonna...

I have just got 5.6% in WRN-40-1 through simply scaling to [-1..1], LOL. This is better than what I've had with any other type of this thing. But does not...