NPU

查看中文

1 Earlier version RKNPU2 SDK

Link to → v1.5.2

2 How to test NPU

2.1 OS

Tested on the following OS:

2.1.1 Debian11 (bullseye)

• rk3588-sd-debian-bullseye-desktop-6.1-arm64-20241011.img.gz

2.1.2 Ubuntu20 (focal)

• rk3588-sd-ubuntu-focal-desktop-6.1-arm64-20241011.img.gz

2.2 install rknpu

cd ~
export GIT_SSL_NO_VERIFY=1
git clone https://github.com/airockchip/rknn-toolkit2.git --depth 1 -b master
cd rknn-toolkit2/rknpu2
sudo cp ./runtime/Linux/librknn_api/aarch64/* /usr/lib
sudo cp ./runtime/Linux/rknn_server/aarch64/usr/bin/* /usr/bin/
sudo cp ./runtime/Linux/librknn_api/include/* /usr/include/

2.3 check rknn version

$ strings /usr/bin/rknn_server |grep 'build@'
2.2.0 (3e10681 build@2024-09-06T10:26:49)
rknn_server version: 2.2.0 (3e10681 build@2024-09-06T10:26:49)
$ strings /usr/lib/librknnrt.so |grep 'librknnrt version:'
librknnrt version: 2.2.0 (c195366594@2024-09-14T12:18:56)

2.4 run rknn_yolov5_demo

sudo apt-get update
sudo apt-get install -y gcc g++ make cmake
 
# fix broken link
cd ~/rknn-toolkit2/rknpu2/examples/3rdparty/mpp/Linux/aarch64
rm -f librockchip_mpp.so librockchip_mpp.so.1
ln -s librockchip_mpp.so.0 librockchip_mpp.so
ln -s librockchip_mpp.so.0 librockchip_mpp.so.1
 
cd ~/rknn-toolkit2/rknpu2/examples/rknn_yolov5_demo
chmod +x ./build-linux.sh
sudo ln -s /usr/bin/gcc /usr/bin/aarch64-gcc
sudo ln -s /usr/bin/g++ /usr/bin/aarch64-g++
export GCC_COMPILER=aarch64
./build-linux.sh -t rk3588 -a aarch64 -b Release
cd install/rknn_yolov5_demo_Linux
./rknn_yolov5_demo model/RK3588/yolov5s-640-640.rknn model/bus.jpg

Transfer the generated out.jpg to PC to view the result:

scp out.jpg xxx@YourIP:/tmp/

2.5 install rknn_toolkit on debian11

2.5.1 install rknn_toolkit

sudo apt-get update
sudo apt-get install -y python3-dev python3-numpy python3-opencv python3-pip
cd ~/rknn-toolkit2
pip3 install ./rknn-toolkit-lite2/packages/rknn_toolkit_lite2-2.2.0-cp39-cp39-linux_aarch64.whl -i https://pypi.tuna.tsinghua.edu.cn/simple/

2.5.2 run python demo

$ cd ~/rknn-toolkit2/rknn-toolkit-lite2/examples/resnet18/
$ python3 test.py
W rknn-toolkit-lite2 version: 2.2.0
--> Load RKNN model
done
--> Init runtime environment
I RKNN: [06:50:39.456] RKNN Runtime Information, librknnrt version: 2.2.0 (c195366594@2024-09-14T12:18:56)
I RKNN: [06:50:39.456] RKNN Driver Information, version: 0.9.3
I RKNN: [06:50:39.456] RKNN Model Information, version: 6, toolkit version: 2.2.0(compiler version: 2.2.0 (c195366594@2024-09-14T12:24:14)), target: RKNPU v2, target platform: rk3588, framework name: PyTorch, framework layout: NCHW, model inference type: static_shape
W RKNN: [06:50:39.474] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
done
--> Running model
resnet18
-----TOP 5-----
[812] score:0.999680 class:"space shuttle"
[404] score:0.000249 class:"airliner"
[657] score:0.000013 class:"missile"
[466] score:0.000009 class:"bullet train, bullet"
[895] score:0.000008 class:"warplane, military plane"
 
done

2.6 install rknn_toolkit on ubuntu-focal

2.6.1 build python3.9 from source

sudo apt install build-essential libssl-dev libffi-dev software-properties-common \
    libbz2-dev libncurses-dev libncursesw5-dev libgdbm-dev liblzma-dev libsqlite3-dev \
    tk-dev libgdbm-compat-dev libreadline-dev
 
wget https://www.python.org/ftp/python/3.9.16/Python-3.9.16.tar.xz
tar -xvf Python-3.9.16.tar.xz
cd Python-3.9.16/
./configure --enable-optimizations
make -j$(nproc)
sudo make install

2.6.2 install rknn_toolkit

python3.9 -m pip install --upgrade pip
python3.9 -m pip install opencv-python
 
cd ~
[ -d rknn-toolkit2 ] || git clone https://github.com/airockchip/rknn-toolkit2.git \
    --depth 1 -b master
cd rknn-toolkit2
python3.9 -m pip install \
    ./rknn-toolkit-lite2/packages/rknn_toolkit_lite2-2.2.0-cp39-cp39-linux_aarch64.whl \
    -i https://pypi.tuna.tsinghua.edu.cn/simple/

2.6.3 run python demo on ubuntu-focal

cd ~/rknn-toolkit2/rknn-toolkit-lite2/examples/resnet18/
python3.9 test.py

output:

W rknn-toolkit-lite2 version: 2.2.0
--> Load RKNN model
done
--> Init runtime environment
I RKNN: [09:57:36.101] RKNN Runtime Information, librknnrt version: 2.2.0 (c195366594@2024-09-14T12:18:56)
I RKNN: [09:57:36.101] RKNN Driver Information, version: 0.9.3
I RKNN: [09:57:36.101] RKNN Model Information, version: 6, toolkit version: 2.2.0(compiler version: 2.2.0 (c195366594@2024-09-14T12:24:14)), target: RKNPU v2, target platform: rk3588, framework name: PyTorch, framework layout: NCHW, model inference type: static_shape
W RKNN: [09:57:36.117] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
done
--> Running model
resnet18
-----TOP 5-----
[812] score:0.999680 class:"space shuttle"
[404] score:0.000249 class:"airliner"
[657] score:0.000013 class:"missile"
[466] score:0.000009 class:"bullet train, bullet"
[895] score:0.000008 class:"warplane, military plane"
 
done

3 Doc

https://github.com/rockchip-linux/rknpu2/tree/master/doc

4 Other

4.1 View NPU Load

cat /sys/kernel/debug/rknpu/load

4.2 Set NPU freq

echo userspace > /sys/class/devfreq/fdab0000.npu/governor
echo 800000000 > /sys/class/devfreq/fdab0000.npu/min_freq
echo 1000000000 > /sys/class/devfreq/fdab0000.npu/max_freq

4.3 View NPU freq

cat /sys/class/devfreq/fdab0000.npu/cur_freq