snncutoff

SNN Cutoff Evaluation.

https://github.com/dengyu-wu/snncutoff

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.3%) to scientific vocabulary

Keywords

neuromorphic-computing snn-cutoff snn-evaluation snn-training spiking-neural-networks
Last synced: 6 months ago · JSON representation ·

Repository

SNN Cutoff Evaluation.

Basic Info
Statistics
  • Stars: 16
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
neuromorphic-computing snn-cutoff snn-evaluation snn-training spiking-neural-networks
Created about 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Citation

.github/readme.md

Text changing depending on mode. Light: 'So light!' Dark: 'So dark!'

SNNCutoff is a Python package developed with a PyTorch backend, designed primarily for evaluating Spiking Neural Networks (SNNs). It offers:

  • SNN Evaluation:

    • Utilizing detailed performance metrics, e.g., accuracy, latency and operations.
    • Capabilities for conducting adaptive inference or cutoff of SNNs.
  • SNN Training:

    • While the emphasis is on evaluation, the toolkit also supports a diverse array of training algorithms.

Overview

  • SNN Training Algorithms:

  • A New Metric:

    • Optimal Cutoff Timestep (OCT): A optimal timestep that determines the minimal input processing duration for maintaining predictive reliability in SNNs. OCT is grounded in theoretical analysis and serves as a robust benchmark for assessing SNN models under different optimization algorithms.
  • Cutoff Approximation:

    • Timestep (Baseline): Cutoff triggered using fixed timestep.
    • Top-K: Cutoff triggered using the gap between the top-1 and top-2 output predictions at each timestep.
    • Others: Coming soon.

More details in Documentation.

Getting Started

To begin using SNNCutoff, clone this repository and follow the setup instructions below.

Installation

  1. Clone the repo sh git clone https://github.com/Dengyu-Wu/snncutoff.git

  2. Install Pytorch sh pip install -r requirements. txt

Training and Evaluation

We provide training and evaluation examples in scripts.

Contributing

Check the contributing guidelines if you want to get involved with developing SNNCutoff.

Acknowledgments

We extend our appreciation to everyone who has contributed to the development of this project, both directly and indirectly.

Owner

  • Name: Dengyu Wu
  • Login: Dengyu-Wu
  • Kind: user
  • Location: United Kingdom
  • Company: University of Liverpool

Citation (CITATION.cff)

cff-version: 1.2.0
type: software
title: SNNCutoff
authors:
- family-names: Wu
  given-names: Dengyu
- family-names: Xu
  given-names: Minghong
# TODO: Issue a DOI for the repo, e.g. 10.5281/zenodo.1234. See:
# https://docs.github.com/en/repositories/archiving-a-github-repository/referencing-and-citing-content
license: MIT
repository-code: https://github.com/Dengyu-Wu/snncutoff
preferred-citation:
  type: article
  title: Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff
  authors:
  - family-names: Wu
    given-names: Dengyu
  - family-names: Jin
    given-names: Gaojie
  - family-names: Yu
    given-names: Han
  - family-names: Yi
    given-names: Xinping
  - family-names: Huang
    given-names: Xiaowei
  year: 2023
  identifiers:
  - type: other
    value: arXiv.2301.09522 [cs.CV]
    description: The ArXiv preprint of the paper
  - type: doi
    value: 10.48550/arXiv.2301.09522
    description: The ArXiv preprint of the paper
  doi: 10.48550/arXiv.2301.09522
  url: https://arxiv.org/abs/2301.09522

GitHub Events

Total
  • Watch event: 4
Last Year
  • Watch event: 4