Mostafa Elhoushi

I believe to obtain a great enhancement like >=5x we need hardware that deals with variables of 4bits (to represent the weights), instead of dealing with variables of 8bits and...

There is a paper in ICLR named APoT (Additive Powers of Two) that did something similar (sum of 2 shifts). Do you want to try their code: https://github.com/yhhhli/APoT_Quantization Hopefully, their...

Also, if you are interested, I think adding weight normalization (before calling `round_power_of_2(...)`) to my DeepShift code might solve the problem of NaN. You can simply do weight normalization by:...

I think we should not modify `self.weight.data`. Can you change the code to: ``` ***@***.***_script_method def forward(self, input): mean = self.weight.data.mean() std = self.weight.data.std() weight_norm = self.weight.data.add(-mean).div(std) weight_norm = ste.clampabs(weight_norm,...

Thanks @Grant-Tao for trying out our repo. In order to help me reproduce the error, can you please provide the command that you ran to get each of the 2...

Hello @Grant-Tao Sorry for the delay in my response. I am just a bit overwhelmed with some other deadlines. I will try to work on solving this problem next week....

Sorry for the delay. We have made a big refactoring of the code. Can you checkout the master branch and try again?

I forgot to say, you will need to run `sh install_kernels.sh` to install the CUDA and CPU kernels.

Hi @msxiaojin - the objective of the cuda/cpp version is to attempt to implement convolution that actually uses bitwise shift rather than multiplication. On the other hand, the convolution with...

> Hello, not sure if I should open a new issue for this, but are the pretrained models trained with default hyperparameters? And do all the pretrained models match the...