Saurabh Dash

Results 6 comments of Saurabh Dash

All of them are required to calculate the gradients for backpropagation

Hi, GAP is not my paper. I just implemented the modules to run the experiments as a weekend hack. I also do not have access to any of the datasets...

The Custom Loss involves a for loop in python which is extremely inefficient. Since the adjacency matrix is small, you can use the default PyTorch backprop for the loss.

> > At the moment, I can only run the 2-bit version due to space. > > 2-bit almost never works well, I don't recommend even trying it.. You can...

Hi! This repository is a bit old but I think you can do that. However, it is going to be slow as the loop is written in Python, if you...

@JenZhao if you implement it, could you please tag me and I'll be happy to review it.