{"id":13442013,"url":"https://github.com/BICLab/EMS-YOLO","last_synced_at":"2025-03-20T13:31:54.643Z","repository":{"id":200299286,"uuid":"668213519","full_name":"BICLab/EMS-YOLO","owner":"BICLab","description":"Offical implementation of \"Deep Directly-Trained Spiking Neural Networks for Object Detection\" (ICCV2023)","archived":false,"fork":false,"pushed_at":"2023-10-15T11:59:31.000Z","size":378,"stargazers_count":146,"open_issues_count":16,"forks_count":13,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-10-28T05:12:34.201Z","etag":null,"topics":["spiking-neural-network","spiking-yolo"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2307.11411","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/BICLab.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,"roadmap":null,"authors":null}},"created_at":"2023-07-19T09:33:15.000Z","updated_at":"2024-10-22T14:27:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"5725f043-6105-4e9b-90ba-5b0b84b7cdff","html_url":"https://github.com/BICLab/EMS-YOLO","commit_stats":null,"previous_names":["biclab/ems-yolo"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BICLab%2FEMS-YOLO","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BICLab%2FEMS-YOLO/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BICLab%2FEMS-YOLO/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BICLab%2FEMS-YOLO/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BICLab","download_url":"https://codeload.github.com/BICLab/EMS-YOLO/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244619148,"owners_count":20482369,"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":["spiking-neural-network","spiking-yolo"],"created_at":"2024-07-31T03:01:40.671Z","updated_at":"2025-03-20T13:31:54.636Z","avatar_url":"https://github.com/BICLab.png","language":"Python","funding_links":[],"categories":["Python","Object Detection Applications","Applications"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\n\n\u003c!--\n\u003ca align=\"center\" href=\"https://ultralytics.com/yolov3\" target=\"_blank\"\u003e\n\u003cimg width=\"800\" src=\"https://github.com/ultralytics/yolov5/releases/download/v1.0/banner-api.png\"\u003e\u003c/a\u003e\n--\u003e\n\n\n\n## \u003cdiv align=\"center\"\u003eDeep Directly-Trained Spiking Neural Networks for Object Detection [(ICCV2023)](https://openaccess.thecvf.com/content/ICCV2023/html/Su_Deep_Directly-Trained_Spiking_Neural_Networks_for_Object_Detection_ICCV_2023_paper.html)\u003c/div\u003e\n\u003c/div\u003e\n\n### Requirements\n\nThe code has been tested with pytorch=1.10.1,py=3.8, cuda=11.3, cudnn=8.2.0_0 . The conda environment can be copied directly via \u003cb\u003eenvironment.yml\u003c/b\u003e. Some additional dependencies can be found in the  \u003cb\u003eenvironment.txt\u003c/b\u003e.\n\n\n\u003cdetails open\u003e\n\u003csummary\u003eInstall\u003c/summary\u003e\n\n```bash\n$ git clone https://github.com/BICLab/EMS-YOLO.git\n$ pip install -r requirements.txt\n```\n\n\u003c/details\u003e\n\n### Pretrained Checkpoints\n\nWe provide the best and the last trained model based on EMS-Res34 on the COCO dataset.\n\n`detect.py` runs inference on a variety of sources, downloading models automatically from\nthe [COCO_EMS-ResNet34](https://drive.google.com/drive/folders/1mry8sdED6ncqxajmQROKBECpcrmXStpB?usp=sharing) .\n\nThe relevant parameter files are in the `runs/train`.\n\n\n### Training \u0026 Addition\n\u003cdetails open\u003e\n\u003csummary\u003eTrain\u003c/summary\u003e\n\nThe relevant code for the Gen1 dataset is at `/g1-resnet`. It needs to be replaced or added to the appropriate root folder.\n\nFor gen1 dataset:\n\n```python\npython path/to/train_g1.py --weights ***.pt --img 640\n```\nFor coco dataset:\n```python\npython train.py\n```\n\u003c/details\u003e\n\n\nCalculating the spiking rate:\n\nDependencies can be downloaded from [Visualizer](https://github.com/luo3300612/Visualizer).\n```python\npython calculate_fr.py\n```\n\n### Contact Information\n\n\n```shell\n@inproceedings{su2023deep,\n  title={Deep Directly-Trained Spiking Neural Networks for Object Detection},\n  author={Su, Qiaoyi and Chou, Yuhong and Hu, Yifan and Li, Jianing and Mei, Shijie and Zhang, Ziyang and Li, Guoqi},\n  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},\n  pages={6555--6565},\n  year={2023}\n}\n```\n\n\u003cp\u003e\nYOLOv3  is a family of object detection architectures and models pretrained on the COCO dataset, and represents \u003ca href=\"https://ultralytics.com\"\u003eUltralytics\u003c/a\u003e\n open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development. \n \n \u003cb\u003eOur code is also implemented in this framework, so please remember to cite their work.\u003c/b\u003e\n\u003c/p\u003e\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FBICLab%2FEMS-YOLO","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FBICLab%2FEMS-YOLO","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FBICLab%2FEMS-YOLO/lists"}