XNOR for ResNet

[XinDongol]

I was wondering whether there is XNOR for ResNet. Or can you give some hints about how to implement it?

[jxgu1016]

Also interested in XNOR for ResNet! @XinDongol have you implemented it yourself?

[25b3nk]

Has anyone implemented XNOR for Resnet ?

[akhauriyash]

I do not mind implementing ResNet for this if there is interest. However, I will not be able to train it.
I think this task mostly just involves changing the class AlexNet here.

[25b3nk]

I have implemented XNOR-net for ResNet. Basically took the resnet.py from torchvision and added the binary Convolution classes from this repo's alexnet.py and then changed the convolutions in resnet.py from nn.Conv2D to BinConv2D.

[XinDongol]

I have implemented ResNet-XNOR and reproduce result of xnor paper. I will release it soon when I have time.

[akhauriyash]

@XinDongol could you kindly share the python models directory code for the ResNet-xNOR with me?
Thanks!

[dorian95]

I have implemented ResNet-XNOR and reproduce result of xnor paper. I will release it soon when I have time.

Could you please share it with me too? Thanks!

[appleleaves]

@XinDongol Would you like to share the python models directory code for the ResNet-XNOR or share the implementation idea?

[blueardour]

@XinDongol Any update on the thread?

[legolas123]

I have implemented the xnornet ++ paper with resnet-18. You can disable alpha, beta, gamma(scale factors for activation) in model file(BinConv2d). Then you can have the xnornet for resnet-18. Btw xnornet++ is improvement over xnornet and my implementation reaches 60% accuracy for 1 bit activation and 1 bit width.
The link is https://github.com/legolas123/cv-tricks.com/tree/master/xnornet_plusplus