Cambricon / CNStream

CNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/SolutionSDK/CNStream

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Cambricon CNStream

CNStream is a streaming framework with plug-ins. It is used to connect other modules, includes basic functionalities, libraries, and essential elements.

CNStream provides the following built-in modules:

  • 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).
  • Inferencer: MLU-based inference accelerator for detection and classification, based on EasyDK InferServer.
  • Osd (On-screen display): Module for highlighting objects and text overlay.
  • VEncode: Encode videos or images and write to file or push RTSP stream to internet.
  • Vout: Display the video on screen (Only support on edge platforms).
  • Tracker: Multi-object tracking.

Getting started

To start using CNStream, please refer to the chapter of quick start in the document of Cambricon-CNStream-User-Guide-CN.pdf .

Samples

Classification Object Detection
Classification Object Detection
Object Tracking License plate recognition
Object Tracking License plate recognition
Body Pose
Body Pose

Best Practices

How to change the input video file?

Modify 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.

Documentation

Cambricon Forum Docs

Check out the Examples page for tutorials on how to use CNStream. Concepts page for basic definitions.

Community forum

Discuss - General community discussion around CNStream.

About

CNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/SolutionSDK/CNStream

License:Apache License 2.0


Languages

Language:C++ 69.5%Language:Python 17.0%Language:CSS 6.1%Language:CMake 3.8%Language:JavaScript 2.7%Language:Shell 0.5%Language:HTML 0.4%