{"id":27078488,"url":"https://github.com/nmhaddad/fast-track","last_synced_at":"2025-04-06T01:03:18.439Z","repository":{"id":65470484,"uuid":"579259357","full_name":"nmhaddad/Fast-Track","owner":"nmhaddad","description":"Object tracking pipelines complete with RF-DETR, YOLOv9, YOLO-NAS, YOLOv8, and YOLOv7 detection and BYTETracker tracking","archived":false,"fork":false,"pushed_at":"2025-04-03T02:27:13.000Z","size":24022,"stargazers_count":70,"open_issues_count":1,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-03T03:19:55.966Z","etag":null,"topics":["computer-vision","deep-learning","object-detection","object-tracking","onnx","opencv","rf-detr","yolo","yolo-nas","yolov7","yolov8","yolov9"],"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/nmhaddad.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE.YOLONAS.md","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}},"created_at":"2022-12-17T04:55:34.000Z","updated_at":"2025-04-03T02:27:15.000Z","dependencies_parsed_at":"2024-02-25T17:30:52.488Z","dependency_job_id":"2fa43428-6792-4966-bddc-7dfd5cd38bf2","html_url":"https://github.com/nmhaddad/Fast-Track","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nmhaddad%2FFast-Track","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nmhaddad%2FFast-Track/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nmhaddad%2FFast-Track/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nmhaddad%2FFast-Track/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nmhaddad","download_url":"https://codeload.github.com/nmhaddad/Fast-Track/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247419858,"owners_count":20936012,"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":["computer-vision","deep-learning","object-detection","object-tracking","onnx","opencv","rf-detr","yolo","yolo-nas","yolov7","yolov8","yolov9"],"created_at":"2025-04-06T01:02:15.458Z","updated_at":"2025-04-06T01:03:18.418Z","avatar_url":"https://github.com/nmhaddad.png","language":"Python","funding_links":[],"categories":["Object Detection Applications"],"sub_categories":[],"readme":"# Fast-Track 🚀 Real-Time Object Tracking Pipelines\n\nInstallable Python package for object tracking pipelines with RF-DETR, YOLOv9, YOLO-NAS, YOLOv8, and YOLOv7 object detectors and BYTETracker object tracking with support for SQL database servers.\n\n[Try it out now with Gradio](#run-the-demo).\n\n![Try out the Gradio Demo!](media/gradio_demo.png)\n\n## Installation:\n\nPackage is installable with Python 3.10, 3.11, and 3.12\n\n1. `git clone \u003crepo\u003e \u0026\u0026 cd \u003crepo\u003e`\n1. `pip install .`\n1. To use ByteTrack object tracking, run: `pip install .[bytetrack]`\n1. To use GPU-enabled ONNX-runtime, run: `pip install .[gpu]`\n1. To use YOLO-NAS object detection, run: `pip install .[yolonas]`\n\n## Running:\n\n1. Example usage RF-DETR:\n    ```\n    import cv2\n    import yaml\n\n    from fast_track import Pipeline\n    from fast_track.detectors import RFDETR\n    from fast_track.trackers import BYTETracker\n    from fast_track.databases import SQLDatabase\n\n\n    with open(\"config/rf-detr.yml\", \"r\") as f:\n        config = yaml.safe_load(f)\n\n    camera = cv2.VideoCapture(config[\"data_path\"])\n    detector = RFDETR(**config[\"detector\"], names=config[\"names\"])\n    tracker = BYTETracker(**config[\"tracker\"], names=config[\"names\"])\n    database = SQLDatabase(**config[\"db\"], class_names=config[\"names\"])\n\n    with Pipeline(\n        camera=camera, detector=detector, tracker=tracker, database=database, outfile=config[\"outfile\"]\n    ) as pipeline:\n        pipeline.run()\n    ```\n\n1. Example usage YOLO-NAS:\n    ```\n    import cv2\n    import yaml\n\n    from fast_track import Pipeline\n    from fast_track.detectors import YOLONAS\n    from fast_track.trackers import BYTETracker\n    from fast_track.databases import SQLDatabase\n\n\n    with open('config/coco.yml', 'r') as f:\n        config = yaml.safe_load(f)\n\n    camera = cv2.VideoCapture(config['data_path'])\n    detector = YOLONAS(**config['detector'], names=config['names'], image_shape=(camera.get(3), camera.get(4)))\n    tracker = BYTETracker(**config['tracker'], names=config['names'])\n    database = SQLDatabase(**config[\"db\"], class_names=config['names'])\n\n    with Pipeline(camera=camera, detector=detector, tracker=tracker, database=database, outfile=config['outfile']) as p:\n        p.run()\n    ```\n\n## Run the Demo\n\nFollow the installation instructions above, then install Gradio with `pip install .[gradio]`\n\nFinally, launch the app with `python app.py`\n\n## Contact:\nAuthor: Nate Haddad - nhaddad2112[at]gmail[dot]com\n\n## License:\n[See LICENSE.txt](LICENSE.txt)\n\n[See YOLO-NAS LICENSE.md](fast_track/detectors/third_party/yolo_nas/LICENSE.md)\n\n[See YOLO-NAS LICENSE.YOLONAS.md](LICENSE.YOLONAS.md)\n\n[See YOLOv8 LICENSE.YOLOv8.txt](LICENSE.YOLOv8.txt)\n\n[See RF-DETR LICENSE.txt](fast_track/detectors/third_party/rfdetr/LICENSE.txt)\n\n## References:\n[1] Jocher, Glenn; \"YOLOv8 in PyTorch \u003e ONNX \u003e CoreML \u003e TFLite\"; https://github.com/ultralytics/; 2023; [Online]. Available: https://github.com/ultralytics/ultralytics \n\n[2] Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark; \"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors\"; https://github.com/WongKinYiu/; 2022; [Online]. Available: https://github.com/WongKinYiu/yolov7\n\n[3] Gorordo, Ibai; \"ONNX YOLOv7 Object Detection\"; https://github.com/ibaiGorordo/; 2022; [Online]. Available: https://github.com/ibaiGorordo/ONNX-YOLOv7-Object-Detection\n\n[4] Zhang, Yifu and Sun, Peize and Jiang, Yi and Yu, Dongdong and Weng, Fucheng and Yuan, Zehuan and Luo, Ping and Liu, Wenyu and Wang, Xinggang; \"ByteTrack: Multi-Object Tracking by Associating Every Detection Box\"; https://github.com/ifzhang; 2022; [Online]. Available: https://github.com/ifzhang/ByteTrack\n\n[5] Aharon, Shay and Louis-Dupont and Ofri Masad and Yurkova, Kate and Lotem Fridman and Lkdci and Khvedchenya, Eugene and Rubin, Ran and Bagrov, Natan and Tymchenko, Borys and Keren, Tomer and Zhilko, Alexander and Eran-Deci; \"Super-Gradients\"; https://github.com/Deci-AI/super-gradients; 2023; [Online]. Available: https://github.com/Deci-AI/super-gradients\n\n[6] Wang, Chien-Yao and Liao, Hong-Yuan Mark; \"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information\"; https://github.com/WongKinYiu/yolov9; 2024; [Online]. Available: https://github.com/WongKinYiu/yolov9\n\n[7] Robinson, Isaac and Robicheaux, Peter and Popov, Matvei; \"RF-DETR\"; https://github.com/roboflow/rf-detr; 2025; [Online]. Available: https://github.com/roboflow/rf-detr\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnmhaddad%2Ffast-track","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnmhaddad%2Ffast-track","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnmhaddad%2Ffast-track/lists"}