{"id":13643258,"url":"https://github.com/Hyuto/yolo-nas-onnx","last_synced_at":"2025-04-21T01:32:18.471Z","repository":{"id":165269619,"uuid":"639542982","full_name":"Hyuto/yolo-nas-onnx","owner":"Hyuto","description":"Inference YOLO-NAS ONNX model","archived":false,"fork":false,"pushed_at":"2023-12-18T07:43:06.000Z","size":68855,"stargazers_count":62,"open_issues_count":3,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-09T15:42:23.619Z","etag":null,"topics":["cpp","javascript","object-detection","onnx","onnxruntime","opencv","opencv-dnn","python","yolo-nas"],"latest_commit_sha":null,"homepage":"https://hyuto.github.io/yolo-nas-onnx/","language":"C++","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/Hyuto.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}},"created_at":"2023-05-11T17:12:12.000Z","updated_at":"2024-08-20T17:26:55.000Z","dependencies_parsed_at":null,"dependency_job_id":"b1b31a77-00c1-4f54-a859-dcc0272d1eeb","html_url":"https://github.com/Hyuto/yolo-nas-onnx","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hyuto%2Fyolo-nas-onnx","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hyuto%2Fyolo-nas-onnx/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hyuto%2Fyolo-nas-onnx/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hyuto%2Fyolo-nas-onnx/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Hyuto","download_url":"https://codeload.github.com/Hyuto/yolo-nas-onnx/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249982596,"owners_count":21355731,"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":["cpp","javascript","object-detection","onnx","onnxruntime","opencv","opencv-dnn","python","yolo-nas"],"created_at":"2024-08-02T01:01:44.685Z","updated_at":"2025-04-21T01:32:13.461Z","avatar_url":"https://github.com/Hyuto.png","language":"C++","funding_links":[],"categories":["Lighter and Deployment Frameworks"],"sub_categories":[],"readme":"# YOLO-NAS ONNX\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./assets/sample-4.jpg\" alt=\"sample\" /\u003e\n\u003c/p\u003e\n\n**_Image Source_**: https://www.pinterest.com/pin/784752303797219490/\n\n---\n\n![love](https://img.shields.io/badge/Made%20with-🖤-white)\n![onnxruntime-web](https://img.shields.io/badge/onnxruntime--web-white?logo=onnx\u0026logoColor=black)\n![opencv](https://img.shields.io/badge/OpenCV-4.7.0-white?logo=opencv)\n![python](https://img.shields.io/badge/Python-darkgreen?logo=python)\n![c++](https://img.shields.io/badge/C++-red?logo=cplusplus)\n![javascript](https://img.shields.io/badge/JavaScript-green?logo=javascript)\n\nRun YOLO-NAS models with ONNX **without using Pytorch**. Inferencing YOLO-NAS ONNX models with ONNXRUNTIME or OpenCV DNN.\n\n## Generate ONNX Model\n\nGenerate YOLO-NAS ONNX model **without preprocessing and postprocessing within the model**.\nYou can convert the model using the following code after installing `super_gradients` library.\n\n**Example: Exporting YOLO-NAS S**\n\n```python\nfrom super_gradients.training import models\nfrom super_gradients.common.object_names import Models\n\nmodel = models.get(Models.YOLO_NAS_S, pretrained_weights=\"coco\")\n\nmodel.eval()\nmodel.prep_model_for_conversion(input_size=[1, 3, 640, 640])\nmodel.export(\"yolo_nas_s.onnx\", postprocessing=None, preprocessing=None)\n```\n\n## Custom Model\n\nTo run custom trained YOLO-NAS model in this project you need to generate custom model metadata.\nCustom model metadata generated from [custom-nas-model-metadata.py](https://gist.github.com/Hyuto/f3db1c0c2c36308284e101f441c2555f)\nto provide additional information from torch model.\n\n**Usage**\n\n```bash\npython custom-nas-model-metadata.py -m \u003cCHECKPOINT-PATH\u003e \\ # Custom trained YOLO-NAS checkpoint path\n                                        -t \u003cMODEL-TYPE\u003e \\ # Custom trained YOLO-NAS model type\n                                        -n \u003cNUM-CLASSES\u003e # Number of classes\n```\n\nAfter running that it'll generate metadata (json formated) for you\n\n## References\n\n- https://github.com/Deci-AI/super-gradients\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHyuto%2Fyolo-nas-onnx","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FHyuto%2Fyolo-nas-onnx","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FHyuto%2Fyolo-nas-onnx/lists"}