{"id":34936353,"url":"https://github.com/cambricon/cnstream","last_synced_at":"2025-12-26T18:10:56.054Z","repository":{"id":40482496,"uuid":"204127962","full_name":"Cambricon/CNStream","owner":"Cambricon","description":"CNStream is a streaming framework for building Cambricon  machine learning pipelines http://forum.cambricon.com    https://gitee.com/SolutionSDK/CNStream","archived":false,"fork":false,"pushed_at":"2025-03-21T07:36:07.000Z","size":271804,"stargazers_count":49,"open_issues_count":5,"forks_count":9,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-03-21T08:28:42.755Z","etag":null,"topics":["c-plus-plus","cambricon","cambricon-cnstream","computer-vision","graph-framework","inference","machine-learning","mlu","pipeline-framework"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Cambricon.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}},"created_at":"2019-08-24T08:05:46.000Z","updated_at":"2025-03-21T07:34:09.000Z","dependencies_parsed_at":"2023-02-09T02:30:51.067Z","dependency_job_id":"5aac0100-051a-4f8e-a296-124e246a1b1d","html_url":"https://github.com/Cambricon/CNStream","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Cambricon/CNStream","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cambricon%2FCNStream","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cambricon%2FCNStream/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cambricon%2FCNStream/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cambricon%2FCNStream/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Cambricon","download_url":"https://codeload.github.com/Cambricon/CNStream/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cambricon%2FCNStream/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28057702,"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":"2025-12-26T02:00:06.189Z","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":["c-plus-plus","cambricon","cambricon-cnstream","computer-vision","graph-framework","inference","machine-learning","mlu","pipeline-framework"],"created_at":"2025-12-26T18:10:48.045Z","updated_at":"2025-12-26T18:10:56.048Z","avatar_url":"https://github.com/Cambricon.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cambricon CNStream #\nCNStream is a streaming framework with plug-ins. It is used to connect other modules, includes basic functionalities, libraries,\nand essential elements.\n\nCNStream provides the following built-in modules:\n\n- DataSource: Support RTSP, video file, images, elementary stream in memory and sensor inputs (H.264, H.265, and JPEG decoding) (sensor input is only supported on edge platforms).\n- Inferencer: MLU-based inference accelerator for detection and classification, based on EasyDK InferServer.\n- Osd (On-screen display): Module for highlighting objects and text overlay.\n- VEncode: Encode videos or images and write to file or push RTSP stream to internet.\n- Vout: Display the video on screen (Only support on edge platforms).\n- Tracker: Multi-object tracking.\n\n### Getting started ###\n\n  To start using CNStream, please refer to the chapter of ***quick start*** in the document of [Cambricon-CNStream-User-Guide-CN.pdf](./docs/release_document/latest/Cambricon-CNStream-User-Guide-CN-vlatest.pdf) .\n## Samples ##\n\n|                        Classification                        |               Object Detection                |\n| :----------------------------------------------------------: | :-------------------------------------------: |\n| \u003cimg src=\"./data/gifs/image_classification.gif\" alt=\"Classification\" style=\"height=350px\" /\u003e | \u003cimg src=\"./data/gifs/object_detection_yolov3.gif\" alt=\"Object Detection\" style=\"height=350px\" /\u003e |\n\n|               Object Tracking               |               License plate recognition               |\n| :-----------------------------------------: | :-----------------------------------------------------: |\n| \u003cimg src=\"./data/gifs/object_tracking.gif\" alt=\"Object Tracking\" style=\"height=350px\" /\u003e | \u003cimg src=\"./data/gifs/lpr.gif\" alt=\"License plate recognition\" style=\"height=350px\" /\u003e |\n\n|                           Body Pose                          |\n| :----------------------------------------------------------: |\n| \u003cimg src=\"./data/gifs/body_pose.gif\" alt=\"Body Pose\" style=\"height=350px\" /\u003e |\n\n## Best Practices ##\n\n### **How to change the input video file?** ##\n\nModify the `files.list_video` file, which is under the `samples` directory, to replace the video path. Each line represents one stream. It is recommended to use an absolute path or use a relative path relative to the executor path.\n\n\n## Documentation ##\n[Cambricon Forum Docs](https://www.cambricon.com/docs/cnstream/user_guide_html/index.html)\n\nCheck out the Examples page for tutorials on how to use CNStream. Concepts page for basic definitions.\n\n## Community forum ##\n[Discuss](http://forum.cambricon.com/list-47-1.html) - General community discussion around CNStream.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcambricon%2Fcnstream","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcambricon%2Fcnstream","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcambricon%2Fcnstream/lists"}