Taewan Ethan Kim
Taewan Ethan Kim
Hi, @vinhkhuc Courtesy of your repo. we got following learning curves for bAbI 1k dataset.   We think above results are almost the same as the MemN2N paper. But,...
@kimhc6028 , Thanks for your well programmed repo. I think following line of code should be modified. It just seems a typo. https://github.com/kimhc6028/pathnet-pytorch/blob/master/pathnet.py#L94 ```y = F.relu(self.fc3[path[1][0]](x)) --> y = F.relu(self.fc3[path[2][0]](x))...