1adrianb / bnn.torch Goto Github PK

Firstly, thank you so much for releasing your code, it helps a lot in understanding your awesome paper!

If I understand the code correctly, for face-alignment, if I want to do everything from the scratch, I have to first train the floating point model using your codebase (https://github.com/1adrianb/face-alignment-training). However, I am missing the link of how you convert this model to the binary model that is available in https://github.com/1adrianb/binary-face-alignment which uses bnn.BinarySpatialConvolution

It seems to me that I need to call the function BinarySpatialConvolution:binarise(convLayer) somehow, but I am a bit confused. Do you have a script which replaces the floating conv modules with their binary counterparts? Do you also train in binary?

I will be very grateful if you can help me out, thanks a lot in advance.

In Binary.lua:
This piece of code:
self.gradInput[input:ge(-1)] = 0 self.gradInput[input:le(-1)] = 0
I think it should be
self.gradInput[input:ge(1)] = 0 self.gradInput[input:le(-1)] = 0
I'm not familiar with lua, correct me if I'm wrong.