Menshykov

@revilokeb Sadly, I'm guessing that the answer lies between Nan, Undefined, {} and []. NVidia guys emailed me that "This feature has been on our radar and we’ll be introducing...

@revilokeb As for the CPU implementations, I don't know of any good CPU implementations in C/C++ either, though it should probably take no more than a few days to develop...

Yes, for fsymbols.org/css/AndroidEmoji.ttf ``` require 'ttfunk' file = TTFunk::File.open("AndroidEmoji.ttf") cmap = file.cmap chars = {} unicode_chars = [] cmap.tables.each do |subtable| next if !subtable.unicode? chars = chars.merge( subtable.code_map ) end...

I did.

≥^.^≤

NVidia doesn't work either.

Well, it gives much different results compared to just scaling to [0..1], that's what I'll tell you. I'm training 28-12 at the moment on the non-distorted dataset and the training...

18.3% error on CIFAR-100 (for 80m params)? Haven't seen any lower numbers published anywhere. Yes, the general WRN architecture seems good and tweakable. Though, with what I've seen, there might...

Here you go. https://github.com/ibmua/Breaking-Cifar I've uploaded the data as well, but you can try to download it via source, just for us to be sure that nothing's wrong. You can...

Sorry for misclicks =X I first thought you've built on top of https://github.com/facebook/fb.resnet.torch , but now I see that their code is pretty different. I wonder what did you build...