{"id":15908292,"url":"https://github.com/jegp/coordinate-regression","last_synced_at":"2025-11-17T13:59:05.560Z","repository":{"id":142393203,"uuid":"528809065","full_name":"Jegp/coordinate-regression","owner":"Jegp","description":"Coordinate regression with biologically realistic neural networks","archived":false,"fork":false,"pushed_at":"2025-06-15T15:13:23.000Z","size":8193,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-07T15:40:20.345Z","etag":null,"topics":["coordinate-regression","event-based-camera","machine-learning","spiking-neural-networks"],"latest_commit_sha":null,"homepage":"https://jegp.github.io/coordinate-regression","language":"Svelte","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Jegp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2022-08-25T10:54:17.000Z","updated_at":"2025-06-15T15:13:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"8ce2a2d0-a111-4b19-868e-eb5ad2000864","html_url":"https://github.com/Jegp/coordinate-regression","commit_stats":{"total_commits":28,"total_committers":4,"mean_commits":7.0,"dds":0.5714285714285714,"last_synced_commit":"abbef279df066716f1c8fc0e40d05dacd046f9e8"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":"emilbaehr/automatic-app-landing-page","purl":"pkg:github/Jegp/coordinate-regression","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fcoordinate-regression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fcoordinate-regression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fcoordinate-regression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fcoordinate-regression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Jegp","download_url":"https://codeload.github.com/Jegp/coordinate-regression/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fcoordinate-regression/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":284893575,"owners_count":27080531,"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","status":"online","status_checked_at":"2025-11-17T02:00:06.431Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["coordinate-regression","event-based-camera","machine-learning","spiking-neural-networks"],"created_at":"2024-10-06T14:20:35.320Z","updated_at":"2025-11-17T13:59:05.530Z","avatar_url":"https://github.com/Jegp.png","language":"Svelte","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Coordinate regression for event-based data\n\nThe repository demonstrates coordinate regression for event-based data with spiking neural networks.\nSpecifically, we contribute:\n\n1. A dataset of event-based vision (EBV) videos for coordinate regression and pose estimation\n2. A method for differentiable coordinate transform (DVS) for spiking neural networks\n3. Translation-invariant receptive fields that outperforms similar artificial neural network models\n\n## Usage\n\nTo train the models, follow the below steps\n\n1. [Download the dataset via this link](https://cloud.jepedersen.dk/s/nXCTBLLS8ZgbQny) and unpack it to a folder you can recall, say `/tmp/eventdata`.\n2. Ensure you have a Python installation with [PyTorch](https://pytorch.org) and [Norse](https://github.com/norse/norse) installed.\n   * After installing the necessary PyTorch version, you can install the dependencies from the `requirements.txt`-file by typing: `pip install -r requirements.txt`\n3. Enter the `coordinate-regression` folder and run the `learn_shapes.py` file with the dataset directory and model type to start training\n   * As an example, run `python learn_shapes.py --data_root=/tmp/eventdata --model=snn`\n     * Four models are available: `ann`, `annsf`, `snn`, and `snnrf`\n     * For training parameter descriptions and help, type `python learn_shapes.py --help`\n\n## Authors and Contact\n\n* Jens E. Pedersen `\u003cjeped@kth.se\u003e` ([Twitter @jensegholm](https://twitter.com/jensegholm))\n* Juan P. Romero B.\n* Jörg Conradt\n\n## Acknowledgements\n\nThis work has been performed at the\n[Neurocomputing Systems Lab](https://neurocomputing.systems) at\n[KTH Royal Institute of Technology](https://kth.se) and funded by the\n[Human Brain Project](https://www.humanbrainproject.eu/) and the\n[AI Pioneer Centre](https://www.aicentre.dk).\n\nPlease cite the work as follows:\n\n```\n@inproceedings{Pedersen_Singhal_Conradt_2023,\n  address={New York, NY, USA},\n  series={NICE ’23},\n  title={Translation and Scale Invariance for Event-Based Object tracking},\n  ISBN={978-1-4503-9947-0},\n  url={https://dl.acm.org/doi/10.1145/3584954.3584996},\n  DOI={10.1145/3584954.3584996},\n  booktitle={Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference}, publisher={Association for Computing Machinery}, author={Pedersen, Jens Egholm and Singhal, Raghav and Conradt, Jorg},\n  year={2023},\n  month=apr,\n  pages={79–85},\n  collection={NICE ’23}\n}\n```\n\n## License\nThis work is licensed under LGPLv3.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjegp%2Fcoordinate-regression","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjegp%2Fcoordinate-regression","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjegp%2Fcoordinate-regression/lists"}