早期版本 Ubuntu22.04 rknn toolkit lite2环境部署

大法师

默认Ubuntu22预装python3.10，暂时与RKNN 本机开发环境不一致，需要单独安装python3.9版本。

step1：增加源

sudo add-apt-repository ppa:deadsnakes/ppa

sudo apt update

sudo apt-mark unhold libexpat1

sudo apt install python3.9* -y

#sudo update-alternatives --list python

#sudo update-alternatives --install /usr/bin/python3 python3  /usr/bin/python3.9 1

#sudo update-alternatives --config python3

setp 2：安装pip3

sudo apt-mark unhold libcurl4

sudo apt install curl -y

curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py

python3.9 get-pip.py

export PATH=/home/ubuntu/.local/bin:$PATH

pip3 -V

pip3 install numpy --upgrade

pip3 install opencv-python

#check opencv
python3.9 -c "import cv2; print(cv2.__version__)"

get-pip.py

step 3：安装rknn toolkit lite2

git clone https://gitee.com/yanyitech/rknpu2.git

sudo cp -arf rknpu2/runtime/RK3588/Linux/librknn_api/aarch64/* /usr/lib/

git clone https://gitee.com/yanyitech/rknn-toolkit2.git

pip3 install rknn-toolkit2/rknn_toolkit_lite2/packages/rknn_toolkit_lite2-1.4.0-cp39-cp39-linux_aarch64.whl

step 4：验证运行环境

cd rknn-toolkit2/rknn_toolkit_lite2/examples/inference_with_lite

ubuntu@coolpi:~/rknn-toolkit2/rknn_toolkit_lite2/examples/inference_with_lite$ python3.9 test.py 
--> Load RKNN model
done
--> Init runtime environment
I RKNN: [10:19:55.691] RKNN Runtime Information: librknnrt version: 1.4.0 (a10f100eb@2022-09-09T09:07:14)
I RKNN: [10:19:55.691] RKNN Driver Information: version: 0.8.0
I RKNN: [10:19:55.691] RKNN Model Information: version: 1, toolkit version: 1.4.0-c15f5e0b(compiler version: 1.4.0 (c73777b51@2022-09-05T12:06:01)), target: RKNPU v2, target platform: rk3588, framework name: PyTorch, framework layout: NCHW
done
--> Running model
resnet18
-----TOP 5-----
[812]: 0.9996696710586548
[404]: 0.0002492684288881719
[657]: 1.632158637221437e-05
[833]: 1.0159346857108176e-05
[466 895]: 9.02384545042878e-06

done

大法师

上述环境操作不适用于新的镜像版本。