{"id":18745257,"url":"https://github.com/erfanzar/objd","last_synced_at":"2025-10-11T05:09:36.046Z","repository":{"id":86840090,"uuid":"532889618","full_name":"erfanzar/ObjD","owner":"erfanzar","description":"smart and strong object detection ai built from scatch with some new features 🚀🚀","archived":false,"fork":false,"pushed_at":"2023-01-27T10:06:42.000Z","size":109173,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-20T07:31:56.340Z","etag":null,"topics":["artificial-intelligence","object-detection","object-detection-model","yolo"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/erfanzar.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,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-09-05T12:25:00.000Z","updated_at":"2023-01-27T09:45:38.000Z","dependencies_parsed_at":null,"dependency_job_id":"bf94e79e-2fc6-4e6f-9fcb-442f966a7c99","html_url":"https://github.com/erfanzar/ObjD","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/erfanzar/ObjD","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erfanzar%2FObjD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erfanzar%2FObjD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erfanzar%2FObjD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erfanzar%2FObjD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/erfanzar","download_url":"https://codeload.github.com/erfanzar/ObjD/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erfanzar%2FObjD/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279006348,"owners_count":26084084,"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":"2025-10-11T02:00:06.511Z","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":["artificial-intelligence","object-detection","object-detection-model","yolo"],"created_at":"2024-11-07T16:17:24.426Z","updated_at":"2025-10-11T05:09:36.041Z","avatar_url":"https://github.com/erfanzar.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# ObjD 🚀\nsmart and strong object detection ai built from scatch with some new features 🚀🚀 (Using some custom CNNs and NeuralNets with a holy help from darknet and yolo for everysingle part and adding a bit of research to it 😂)\n\n\n![Logo](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/th5xamgrr6se0x5ro4g6.png)\n\n\n## Contributing\n\nContributions are always welcome!\n\nSee `contributing.md` for ways to get started.\n\nPlease adhere to this project's `code of conduct`.\n\n\n## Training\n\nTo train ObjD you don't have to do crazy things you just have to pick one of the models and train that with custom data that you want to train ObjD with :)\n\n\nHelp For Training \n\n*ArgParses*\n\n\n`cfg`\n```bash\n  python3 torch_train.py --cfg \u003cconfig/config.yaml\u003e\n```\n\n`data`\n```bash\n  python3 torch_train.py --data \u003cdata/path.yaml\u003e\n```\n\n\n`epochs`\n```bash\n  python3 torch_train.py --epochs \u003c300\u003e\n```\n\n\n`eval`\n```bash\n  python3 torch_train.py --eval\n```\n\n\n`debug`\n```bash\n  python3 torch_train.py --debug\n```\n\n\n\n`device`\n```bash\n  python3 torch_train.py --device \u003c'cuda:0'\u003e\n```\n\n\n\n`auto anchors`\n```bash\n  python3 torch_train.py --auto-anchors\n```\n## Model Reference (ObjD)\n\n| Model             | Param     |  Accuracy | FPS|                           \n| ----------------- | -----------|- | -|\n| ObjD tiny | `~ M` |accuracy on COCO data 50 %| `FPS 80`|\n| ObjD s | `~ M` |accuracy on COCO data 59 %| `FPS 72`|\n| ObjD n | `~ M` |accuracy on COCO data 68 %| `FPS 60`|\n| ObjD hx | `~ M`|accuracy on COCO data 77 %| `FPS 43`|\n\n\n\n## Types\n\n#### About \n\nthere are 2 types of training methods \n \n\n- [PytorchLightning](https://github.com/erfanzar/ObjD/blob/main/train.py)\n- [Native Pytorch](https://github.com/erfanzar/ObjD/blob/main/torch_train.py)\n\nthey both have some benefits and the both are hackable to make them more customize and its depends on you to choose which way you want to train your model with but i recommend yo use native pytorch cause that one have better work and stabelity right now\n\n#### PytorchLightning \n\n```bash\n  python3 train.py \n```\n\n#### Native Pytorch\n\n```python\n    python3 torch_train.py \n```\n\n\n\n\n\n## 🚀 About Me\nHi there 👋\nI like to train deep neural nets on large datasets 🧠.\nAmong other things in this world:)\n\n## License\n\n[MIT](https://choosealicense.com/licenses/mit/)\n\n\n## Used By\n\nThis project is used by the following companies:\n\n- You Can Be First One Here :)\n\n\n\n## Author\n\n- [@erfanzar](https://www.github.com/erfanzar)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferfanzar%2Fobjd","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ferfanzar%2Fobjd","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferfanzar%2Fobjd/lists"}