Special made for the NPU, see Q-engineering deep learning examples

All models, with C++ examples can be found on the SD images.

Rock 5 with Ubuntu 22.04, OpenCV, ncnn and NPU

Radxa Zero 3 with Ubuntu 22.04, OpenCV, ncnn and NPU

All models are quantized to int8, unless otherwise noted.

¹ Input size 320x320
² Input size 480x480
³ Input size 48x320, FP16

• Due to the pixel-wise filling and drawing, segmentation models are relatively slow

To run the application, you have to:

• OpenCV 64-bit installed.
• Code::Blocks installed. ($ sudo apt-get install codeblocks)

Start with the usual

$ sudo apt-get update 
$ sudo apt-get upgrade
$ sudo apt-get install cmake wget curl

Follow the Raspberry Pi 4 guide.

$ git clone https://github.com/airockchip/rknn-toolkit2.git

We only use a few files.

rknn-toolkit2-master
│      
└── rknpu2
    │      
    └── runtime
        │       
        └── Linux
            │      
            └── librknn_api
                ├── aarch64
                │   └── librknnrt.so
                └── include
                    ├── rknn_api.h
                    ├── rknn_custom_op.h
                    └── rknn_matmul_api.h

$ cd ~/rknn-toolkit2-master/rknpu2/runtime/Linux/librknn_api/aarch64
$ sudo cp ./librknnrt.so /usr/local/lib
$ cd ~/rknn-toolkit2-master/rknpu2/runtime/Linux/librknn_api/include
$ sudo cp ./rknn_* /usr/local/include

Save 2 GB of disk space by removing the toolkit. We do not need it anymore.

$ cd ~
$ sudo rm -rf ./rknn-toolkit2-master

To extract and run the network in Code::Blocks

$ mkdir *MyDir* <br/>
$ cd *MyDir* <br/>
$ git clone https://github.com/Qengineering/YoloV6-NPU.git <br/>

You can use Code::Blocks.

• Load the project file *.cbp in Code::Blocks.
• Select Release, not Debug.
• Compile and run with F9.
• You can alter command line arguments with Project -> Set programs arguments...

Or use Cmake.

$ cd *MyDir*
$ mkdir build
$ cd build
$ cmake ..
$ make -j4

Make sure you use the model fitting your system.

More info or if you want to connect a camera to the app, follow the instructions at Hands-On.