search

allenai / XNOR-Net

ImageNet classification using binary Convolutional Neural Networks
https://xnor.ai/
Other
856 stars 239 forks source link

Binary Convolutional layer #20

Open deepsemantic opened 7 years ago

deepsemantic commented 7 years ago

Hi, thanks for sharing the code, where can I find the implementation of binary Convolutional layer? I only find "BinActiveZ.lua"

iridescent303 commented 7 years ago

I can't find the K which is metioned in the paper in the codes , do you find it?

Dashhh commented 7 years ago

@iridescent303 according to the paper

We found that the scaling factors for the weights (α) is much more effective than the scaling factors for the inputs (β). Removing β reduces the accuracy by a small margin (less than 1% top-1 alexnet).

I think they are simply omitting it.

iridescent303 commented 7 years ago

@Dashhh yeah, I have found only using scaling factor for the inputs instead of K can also get the similar result.

Lanweichao commented 4 years ago

@Dashhh yeah, I have found only using scaling factor for the inputs instead of K can also get the similar result.

hello, I also think they omit the K. Could you tell me where the scaling factor were used in their codes since I did not find it? Thank you very much.