aa-samad / conv_snn

Code for "Convolutional spiking neural networks (SNN) for spatio-temporal feature extraction" paper

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Residual and downsample

arkhodamoradi opened this issue · comments

The default settings in main.py prevents downsampling unit at here: https://github.com/aa-samad/conv_snn/blob/master/CIFAR10-DVS/network.py#L131

Therefore, network is without residual path: https://github.com/aa-samad/conv_snn/blob/master/CIFAR10-DVS/network.py#L81

Do we need downsampling for the residual path? Does the example network supposed to be without a residual path?

miss reading the code.