search

miladmozafari / SpykeTorch

High-speed simulator of convolutional spiking neural networks with at most one spike per neuron.
GNU General Public License v3.0
382 stars 101 forks source link

global pooling in KheradpishehDeep.py #8

Closed wang1239435478 closed 3 years ago

wang1239435478 commented 3 years ago

Hi miladmozafari. Thanks for providing such a useful toolbox for building convolutional spiking neural networks. I am trying to implement Kheradpisheh's work using your script (KheradpishehDeep.py). However, I found that in Kheradpisheh's paper the threshold of neurons in the last convolutional layer were set to be infinite and the global pooling was performed for classification, which is inconsistent with your code. Would you please explain this?

miladmozafari commented 3 years ago

Hi wang1239435478, Sorry for the late response. Now that I read the paper again, there is an inconsistency in the Methods and the Results sections about the threshold of the last conv layer. I implemented this code based on the explanations in the Results section. But I might have understood it incorrectly. You can contact the authors of the reference paper for better clarification.

wang1239435478 commented 3 years ago

Thanks for your reply.