Menshykov

Lol, so I've tried using ResNet to learn the best preprocessing and it basically decided that leaving it as it is, maybe, just tweaking the mean, is the best way...

You may also want to try out that mean and std preprocessing I've posted, or more simply. ``` cifar10 = torch.load("/path/cifar.t7") function prepare( d , res ) m = torch.mean(...

Yes, code in those both places is per-channel. You can also find it above in this thread. I've tried benchmarking different approaches and haven't noticed any distinctive difference. It would...

@szagoruyko , when you'll be publishing an update, please include a figure with dots mapped on accuracy and #parameters (computation time in another figure). That would help. Also, maybe, a...

@szagoruyko You might also want to try to disable padding, or at least set it to zero-padding instead of reflect-padding, as it will be easier to compare your models with...

Cifar performs pretty awfully with that arch, though.

OMFG! Thanks for that paper, it's totally the same concept as I've recently figured out and had been testing. NNs grow up by days, not years right now.

Yes, as far as I see from their pictures, it's nearly identical to my hoardNet, so you might as well just use my code, maybe, modify it a little bit....

Their code is also available. At https://github.com/liuzhuang13/DenseNet/blob/master/densenet.lua . They are using preactivation, which is different from what I've used. I thought that that may be beneficial, but that needed more...

Mean+std is likely a little bit better.