FTC-SNN

FTC-SNN: Boosting Spiking Neural Networks via Fourier and Cross-Temporal Constraint

This paper has been submitted to Neurocomputing. The complete code will be made public when our paper is accepted.

Requirements

• Python 3.9.7
• Torch 1.10.1
• Torchvision 0.11.2
• Numpy 1.22.0

Datasets

• CIFAR10
• CIFAR100
• DVS-CIFAR10
• N-Caltech101

TO DO

The complete layers.py/models.py/train.py script will be release soon.

• This inference weight is to reproduce 83.70% on DVS-CIFAR10 with VGGSNN.Inference model