Pytorch implementation code for [Neural Architecture Search for Spiking Neural Networks]

Related tags

Deep Learning Neural-Architecture-Search-for-Spiking-Neural-Networks
Overview

Neural Architecture Search for Spiking Neural Networks

Pytorch implementation code for [Neural Architecture Search for Spiking Neural Networks] (https://arxiv.org/abs/2201.10355)

For getting knowledge on NAS without training in ANN domain (refer: https://github.com/BayesWatch/nas-without-training)

Prerequisites

  • Python 3.9
  • PyTorch 1.10.0
  • NVIDIA GPU (>= 12GB)
  • CUDA 10.2 (optional)

Getting Started

Conda Environment Setting

conda create -n SNASNet 
conda activate SNASNet
conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch
pip install scipy

Spikingjelly Installation (ref: https://github.com/fangwei123456/spikingjelly)

git clone https://github.com/fangwei123456/spikingjelly.git
cd spikingjelly
python setup.py install

Training and testing

  • Arguments required for training and testing are contained in ``config.py```
  • Here is an example of running an experiment on CIFAR100
  • (if a user want to skip search process and use predefined architecgtur) A architecture can be parsed by --cnt_mat 0302 0030 3003 0000 format

Example) Architecture and the corresponding connection matrix

Training

  • Run the following command
python search_snn.py  --exp_name 'cifar100_backward' --dataset 'cifar100'  --celltype 'backward' --batch_size 32 --num_search 5000

simple argument instruction

--exp_name: savefile name

--dataset: dataset for experiment

--celltype: find backward connections or forward connections

--num_search: number of architecture candidates for searching

Testing (on pretrained model)

  • As a first step, download pretrained parameters (link) to ./savemodel/save_cifar100_bw.pth.tar

  • The above pretrained model is for CIFAR100 / architecture --cnt_mat 0302 0030 3003 0000

  • Run the following command

python search_snn.py  --dataset 'cifar100' --cnt_mat 0302 0030 3003 0000 --savemodel_pth './savemodel/save_cifar100_bw.pth.tar'  --celltype 'backward'
You might also like...
PyTorch implementation of
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

Efficient Neural Architecture Search (ENAS) in PyTorch PyTorch implementation of Efficient Neural Architecture Search via Parameters Sharing. ENAS red

Taehoon Kim 2.6k Dec 31, 2022
An implementation for Neural Architecture Search with Random Labels (CVPR 2021 poster) on Pytorch.
An implementation for Neural Architecture Search with Random Labels (CVPR 2021 poster) on Pytorch.

Neural Architecture Search with Random Labels(RLNAS) Introduction This project provides an implementation for Neural Architecture Search with Random L

null 18 Nov 8, 2022
Differentiable architecture search for convolutional and recurrent networks
Differentiable architecture search for convolutional and recurrent networks

Differentiable Architecture Search Code accompanying the paper DARTS: Differentiable Architecture Search Hanxiao Liu, Karen Simonyan, Yiming Yang. arX

Hanxiao Liu 3.7k Jan 9, 2023
Code release to accompany paper "Geometry-Aware Gradient Algorithms for Neural Architecture Search."

Geometry-Aware Gradient Algorithms for Neural Architecture Search This repository contains the code required to run the experiments for the DARTS sear

null 18 May 27, 2022
code for "AttentiveNAS Improving Neural Architecture Search via Attentive Sampling"

code for "AttentiveNAS Improving Neural Architecture Search via Attentive Sampling"

Facebook Research 94 Oct 26, 2022
Code repository accompanying the paper "On Adversarial Robustness: A Neural Architecture Search perspective"

On Adversarial Robustness: A Neural Architecture Search perspective Preparation: Clone the repository: https://github.com/tdchaitanya/nas-robustness.g

Chaitanya Devaguptapu 4 Nov 10, 2022
GEA - Code for Guided Evolution for Neural Architecture Search

Efficient Guided Evolution for Neural Architecture Search Usage Create a conda e

null 6 Jan 3, 2023
Official implementation of Rethinking Graph Neural Architecture Search from Message-passing (CVPR2021)
Official implementation of Rethinking Graph Neural Architecture Search from Message-passing (CVPR2021)

Rethinking Graph Neural Architecture Search from Message-passing Intro The GNAS can automatically learn better architecture with the optimal depth of

Shaofei Cai 48 Sep 30, 2022
Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.
Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Deep Image Search - AI-Based Image Search Engine Deep Image Search is an AI-based image search engine that includes deep transfer learning features Ex

null 139 Jan 1, 2023
Comments
Owner
Intelligent Computing Lab at Yale University
Intelligent Computing Lab at Yale University
GitHub
PyTorch implementation of Spiking Neural Networks trained on surrogate gradient & BPTT using snntorch.

snn-localization repo PyTorch implementation of Spiking Neural Networks trained on surrogate gradient & BPTT using snntorch. Install Dependencies Orig

Sami BARCHID 1 Jan 6, 2022
code for paper "Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?"

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? Code for paper: Does Unsupervised Architecture Representation

null 39 Dec 17, 2022
Deep learning for spiking neural networks

A deep learning library for spiking neural networks. Norse aims to exploit the advantages of bio-inspired neural components, which are sparse and even

Electronic Vision(s) Group — BrainScaleS Neuromorphic Hardware 59 Nov 28, 2022
A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

Rockpool Rockpool is a Python package for developing signal processing applications with spiking neural networks. Rockpool allows you to build network

SynSense 21 Dec 14, 2022
Deep and online learning with spiking neural networks in Python

Introduction The brain is the perfect place to look for inspiration to develop more efficient neural networks. One of the main differences with modern

Jason Eshraghian 447 Jan 3, 2023
Spiking Neural Network for Computer Vision using SpikingJelly framework and Pytorch-Lightning

Spiking Neural Network for Computer Vision using SpikingJelly framework and Pytorch-Lightning

Sami BARCHID 2 Oct 20, 2022
Densely Connected Search Space for More Flexible Neural Architecture Search (CVPR2020)

DenseNAS The code of the CVPR2020 paper Densely Connected Search Space for More Flexible Neural Architecture Search. Neural architecture search (NAS)

Jamin Fong 291 Nov 18, 2022
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks

What is DeepHyper? DeepHyper is a software package that uses learning, optimization, and parallel computing to automate the design and development of

DeepHyper Team 214 Jan 8, 2023
Model search is a framework that implements AutoML algorithms for model architecture search at scale

Model search (MS) is a framework that implements AutoML algorithms for model architecture search at scale. It aims to help researchers speed up their exploration process for finding the right model architecture for their classification problems (i.e., DNNs with different types of layers).

Google 3.2k Dec 31, 2022
Official PyTorch implementation of "Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets" (ICLR 2021)

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets This is the official PyTorch implementation for the paper Rapid Neural A

null 48 Dec 26, 2022