https://github.com/cambricon/cnstream
CNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/SolutionSDK/CNStream
https://github.com/cambricon/cnstream
c-plus-plus cambricon cambricon-cnstream computer-vision graph-framework inference machine-learning mlu pipeline-framework
Last synced: 3 months ago
JSON representation
CNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/SolutionSDK/CNStream
- Host: GitHub
- URL: https://github.com/cambricon/cnstream
- Owner: Cambricon
- License: apache-2.0
- Created: 2019-08-24T08:05:46.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2025-03-21T07:36:07.000Z (about 1 year ago)
- Last Synced: 2025-03-21T08:28:42.755Z (about 1 year ago)
- Topics: c-plus-plus, cambricon, cambricon-cnstream, computer-vision, graph-framework, inference, machine-learning, mlu, pipeline-framework
- Language: C++
- Homepage:
- Size: 259 MB
- Stars: 49
- Watchers: 9
- Forks: 9
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 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](./docs/release_document/latest/Cambricon-CNStream-User-Guide-CN-vlatest.pdf) .
## Samples ##
| Classification | Object Detection |
| :----------------------------------------------------------: | :-------------------------------------------: |
| 
| 
|
| Object Tracking | License plate recognition |
| :-----------------------------------------: | :-----------------------------------------------------: |
| 
| 
|
| 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](https://www.cambricon.com/docs/cnstream/user_guide_html/index.html)
Check out the Examples page for tutorials on how to use CNStream. Concepts page for basic definitions.
## Community forum ##
[Discuss](http://forum.cambricon.com/list-47-1.html) - General community discussion around CNStream.