{"id":13437738,"url":"https://github.com/SonwYang/YoloX-TensorRT-webcam","last_synced_at":"2025-03-19T18:30:37.637Z","repository":{"id":127711350,"uuid":"430607840","full_name":"SonwYang/YoloX-TensorRT-webcam","owner":"SonwYang","description":null,"archived":false,"fork":false,"pushed_at":"2021-11-24T00:24:44.000Z","size":18856,"stargazers_count":9,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-27T23:23:31.168Z","etag":null,"topics":["tensorrt8x","webcam","windows"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SonwYang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2021-11-22T07:40:56.000Z","updated_at":"2023-06-17T16:06:44.000Z","dependencies_parsed_at":"2023-08-17T07:00:10.826Z","dependency_job_id":null,"html_url":"https://github.com/SonwYang/YoloX-TensorRT-webcam","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/SonwYang%2FYoloX-TensorRT-webcam","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SonwYang%2FYoloX-TensorRT-webcam/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SonwYang%2FYoloX-TensorRT-webcam/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SonwYang%2FYoloX-TensorRT-webcam/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SonwYang","download_url":"https://codeload.github.com/SonwYang/YoloX-TensorRT-webcam/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244483104,"owners_count":20460056,"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":["tensorrt8x","webcam","windows"],"created_at":"2024-07-31T03:00:59.852Z","updated_at":"2025-03-19T18:30:36.159Z","avatar_url":"https://github.com/SonwYang.png","language":"C++","funding_links":[],"categories":["C++"],"sub_categories":[],"readme":"# YOLOX-TensorRT(8.2.0.6) in webcam\n\nThe repo is a complement to the official repo. There are three differences:\n\n- Windows 10\n- TensorRT 8.2.0.6\n- Webcam\n\n\n\n![conv_ops](result.gif)\n\n\n## Step 1: Prepare serialized engine file\n\nFollow the trt [python demo README](https://github.com/Megvii-BaseDetection/YOLOX/blob/main/demo/TensorRT/python/README.md) to convert and save the serialized engine file.\n\nCheck the 'model_trt.engine' file generated from Step 1, which will be automatically saved at the current demo dir.\n\n\n## Step 2: build the demo\n\nPlease follow the [TensorRT Installation Guide](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html) to install TensorRT.\n\nAnd you should set the TensorRT path and CUDA path in CMakeLists.txt.\n\nIf you train your custom dataset, you may need to modify the value of `num_class`.\n\n```c++\nconst int num_class = 80;\n```\n\nInstall opencv with ```sudo apt-get install libopencv-dev``` (we don't need a higher version of opencv like v3.3+). \n\nbuild the demo:\n## Step 2: build the demo\n\nPlease follow the [TensorRT Installation Guide](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html) to install TensorRT.\n\nAnd you should set the TensorRT path, OpenCV path and CUDA path in CMakeLists.txt.\n\nIf you train your custom dataset, you may need to modify the value of `num_class`.\n\n```c++\nconst int num_class = 80;\n```\n\nbuild the demo:\n\n1. Building the project through cmake -gui.exe\n2. Generating yolox.exe from VS  \n\nrun the demo:\n\n```shell\nyolox.exe ../model_trt.engine -i\n```\n\nor\n\n```shell\nyolox.exe \u003cpath/to/your/engine_file\u003e -i\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSonwYang%2FYoloX-TensorRT-webcam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FSonwYang%2FYoloX-TensorRT-webcam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSonwYang%2FYoloX-TensorRT-webcam/lists"}