Your Name 4ed3c4ac1d 修改: source/common/kafka_handler/kafkahandler_default.cpp | преди 2 години | |
---|---|---|
.github | преди 2 години | |
3rdparty | преди 2 години | |
cmake | преди 2 години | |
data | преди 2 години | |
docker | преди 2 години | |
easydk | преди 2 години | |
framework | преди 2 години | |
modules | преди 2 години | |
modules_contrib | преди 2 години | |
python | преди 2 години | |
source | преди 2 години | |
tools | преди 2 години | |
.dockerignore | преди 2 години | |
.gitignore | преди 2 години | |
.gitmodules | преди 2 години | |
CMakeLists.txt | преди 2 години | |
CPPLINT.cfg | преди 2 години | |
README.md | преди 2 години |
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:
To start using CNStream, please refer to the chapter of quick start in the document of Cambricon-CNStream-User-Guild-CN.pdf.
Classification | Object Detection |
---|---|
Object Tracking | License plate recognization |
---|---|
Body Pose | Vehicle Detection |
---|---|
You should find a sample from samples/simple_run_pipeline/simple_run_pipeline.cpp
that helps developers easily understand how to develop a classic classification or detection application based on CNStream pipeline.
This sample supports typical classification and detection neural networks like vgg resnet ssd fasterrcnn yolo-vx and so on.
This sample supports images or video file as input.
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.
Check out the Examples page for tutorials on how to use CNStream. Concepts page for basic definitions.
Discuss - General community discussion around CNStream.