{"id":13712745,"url":"https://github.com/aa-samad/conv_snn","last_synced_at":"2025-05-06T22:31:25.890Z","repository":{"id":196694386,"uuid":"238659811","full_name":"aa-samad/conv_snn","owner":"aa-samad","description":"Code for \"Convolutional spiking neural networks (SNN) for spatio-temporal feature extraction\" paper","archived":false,"fork":false,"pushed_at":"2020-10-22T07:25:52.000Z","size":77,"stargazers_count":111,"open_issues_count":10,"forks_count":27,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-02-17T11:32:13.978Z","etag":null,"topics":["cifar10","cnn","convolutional-neural-networks","deep-learning","neuromorphic","pytorch","snn","spatio-temporal-analysis"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aa-samad.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-02-06T10:12:59.000Z","updated_at":"2024-02-12T22:20:05.000Z","dependencies_parsed_at":"2023-09-27T01:02:27.555Z","dependency_job_id":null,"html_url":"https://github.com/aa-samad/conv_snn","commit_stats":null,"previous_names":["aa-samad/conv_snn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aa-samad%2Fconv_snn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aa-samad%2Fconv_snn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aa-samad%2Fconv_snn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aa-samad%2Fconv_snn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aa-samad","download_url":"https://codeload.github.com/aa-samad/conv_snn/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252779067,"owners_count":21802876,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cifar10","cnn","convolutional-neural-networks","deep-learning","neuromorphic","pytorch","snn","spatio-temporal-analysis"],"created_at":"2024-08-02T23:01:22.164Z","updated_at":"2025-05-06T22:31:25.461Z","avatar_url":"https://github.com/aa-samad.png","language":"Python","funding_links":[],"categories":["Uncategorized","Applications"],"sub_categories":["Uncategorized","Papers"],"readme":"# Conv-SNN\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/convolutional-spiking-neural-networks-for/event-data-classification-on-cifar10-dvs)](https://paperswithcode.com/sota/event-data-classification-on-cifar10-dvs?p=convolutional-spiking-neural-networks-for)\n### Convolutional spiking neural networks (SNN) for spatio-temporal feature extraction\nThis paper highlights potentials of Convolutional spiking neural networks and introduces a new architecture to tackle training deep convolutional SNN problems.\n\n## Prerequisites\nThe Following Setup is tested and it is working:\n- Python\u003e=3.5\n- Pytorch\u003e=0.4.1\n- Cuda\u003e=9.0\n- opencv\u003e=3.4.2\n\n## Docker\n- Set up the environment where all the programs can run\n    + Run ```./run.sh```\n\n## Data preparation\n- Download CIFAR10-DVS dataset\n    + Extract the dataset under DVS-CIFAR10/dvs-cifar10 folder\n    + Use test_dvs.m in matlab to convert events into matrix of ```t, x, y, p``` (make sure to adjust the test_dvs.m folder addresses inside the code)\n    + Run ```python3 dvscifar_dataloader.py``` to prepare the dataset (make sure to have files like dvs-cifar10/airplane/0.mat inside main.py directory)\n\n## Training \u0026 Testing\n- CIFAR10-DVS model\n    + Run ```python3 main.py```\n\n\n- Spatio-temporal feature extraction tests\n    + For each architecture simply run main file with python3\n\n\n- Note: There are problems with training SNNs, such as extreme importance of initialization; Therefore, you may not reach the highest accuracy as mentioned in the paper.\nThe solution is to try other torch versions and parameters or contact me / make an issue if you truly need the highest accuracy.\n\n## Citing\nPlease adequately refer to the papers any time this Work is being used. If you do publish a paper where this Work helped your research, Please cite the following papers in your publications.\n\n\t@misc{samadzadeh2020convolutional,\n            title={Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction},\n            author={Ali Samadzadeh and Fatemeh Sadat Tabatabaei Far and Ali Javadi and Ahmad Nickabadi and Morteza Haghir Chehreghani},\n            year={2020},\n            eprint={2003.12346},\n            archivePrefix={arXiv},\n            primaryClass={cs.CV}\n        }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faa-samad%2Fconv_snn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faa-samad%2Fconv_snn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faa-samad%2Fconv_snn/lists"}