Effective Conversion of a Convolution Neural Network into a Spiking Neural Network for Image Recognition Tasks

This is the code related to the paper titled "Effective Conversion of a Convolution Neural Network into a Spiking Neural Network for Image Recognition Tasks" in MDPI 2022

Files

'source_code/cnn_train.py': Training a CNN model on MNIST dataset.
'source_code/nets.py': CNN architecture to train MNIST dataset. And a corresponding SNN architecture for inference
'source_code/neurons.py': spiking neurons classes
'source_code/snn_inference.py': Perform a CNN-SNN conversion with our proposed method
'source_code/utils.py': conists of our proposed threshold balancing technique and other functions