Article Directory
Paddle Lite environment preparation
Hardware preparation
- Raspberry Pi 4B
- usb camera
- SD card with Buster mirror source installed
Basic software environment preparation
Camera preparation
Reference article: Installation, configuration and verification of Raspberry Pi camera
Compilation library preparation
Complete the installation of gcc, g++, opencv, cmake:
sudo apt-get update
sudo apt-get install gcc g++ make wget unzip libopencv-dev pkg-config
#下载cmake
wget https://www.cmake.org/files/v3.10/cmake-3.10.3.tar.gz
If the download is slow at this step, I also provide the cmake-3.10.3.tar.gz package , and you can download it yourself .
#解压
tar -zxvf cmake-3.10.3.tar.gz
#进入文件夹
cd cmake-3.10.3
#环境配置
sudo ./configure
#make
sudo make
sudo make install
All the environmental preparations have been completed here.
Download Paddle-Lite
For students who have a slow git clone, please refer to the blog: How to speed up git clone
# 1. 下载Paddle-Lite源码 并切换到release分支
git clone https://github.com/PaddlePaddle/Paddle-Lite.git
cd Paddle-Lite && git checkout release/v2.6
# 删除此目录,编译脚本会自动从国内CDN下载第三方库文件
rm -rf third-party
Compile
cd Paddle-Lite
./lite/tools/build_linux.sh --arch=armv7hf --with_python=ON --python_version=3.7 --with_extra=ON --with_cv=ON
Compilation options
./lite/tools/build_linux.sh help
- Specific options
--------------------------------------------------------------------------------------------------------------------------------------------------------
| Methods of compiling Padddle-Lite Linux library: |
--------------------------------------------------------------------------------------------------------------------------------------------------------
| compile linux library: (armv8, gcc) |
| ./lite/tools/build_linux.sh |
| print help information: |
| ./lite/tools/build_linux.sh help |
| |
| optional argument: |
| --arch: (armv8|armv7hf|armv7), default is armv8 |
| --toolchain: (gcc|clang), defalut is gcc |
| --with_extra: (OFF|ON); controls whether to publish extra operators and kernels for (sequence-related model such as OCR or NLP), default is OFF |
| --with_python: (OFF|ON); controls whether to build python lib or whl, default is OFF |
| --python_version: (2.7|3.5|3.7); controls python version to compile whl, default is None |
| --with_cv: (OFF|ON); controls whether to compile cv functions into lib, default is OFF |
| --with_log: (OFF|ON); controls whether to print log information, default is ON |
| --with_exception: (OFF|ON); controls whether to throw the exception when error occurs, default is OFF |
| |
| arguments of striping lib according to input model: |
| ./lite/tools/build_linux.sh --with_strip=ON --opt_model_dir=YourOptimizedModelDir |
| --with_strip: (OFF|ON); controls whether to strip lib accrding to input model, default is OFF |
| --opt_model_dir: (absolute path to optimized model dir) required when compiling striped library |
| detailed information about striping lib: https://paddle-lite.readthedocs.io/zh/latest/user_guides/library_tailoring.html |
| |
| arguments of opencl library compiling: |
| ./lite/tools/build_linux.sh --with_opencl=ON |
| --with_opencl: (OFF|ON); controls whether to compile lib for opencl, default is OFF |
| |
| arguments of rockchip npu library compiling: |
| ./lite/tools/build_linux.sh --with_rockchip_npu=ON --rockchip_npu_sdk_root=YourRockchipNpuSdkPath |
| --with_rockchip_npu: (OFF|ON); controls whether to compile lib for rockchip_npu, default is OFF |
| --rockchip_npu_sdk_root: (path to rockchip_npu DDK file) required when compiling rockchip_npu library |
| |
| arguments of baidu xpu library compiling: |
| ./lite/tools/build_linux.sh --with_baidu_xpu=ON --baidu_xpu_sdk_root=YourBaiduXpuSdkPath |
| --with_baidu_xpu: (OFF|ON); controls whether to compile lib for baidu_xpu, default is OFF |
| --baidu_xpu_sdk_root: (path to baidu_xpu DDK file) required when compiling baidu_xpu library |
--------------------------------------------------------------------------------------------------------------------------------------------------------
Compilation is complete
Install the compiled python paddle-lite package
进入dist目录下
cd /Paddle-Lite/build.lite.linux.armv7hf.gcc/inference_lite_lib.armlinux.armv7hf/python/install/dist
pip3 install paddlelite-2708c2fe-cp37-cp37m-linux_armv7l.whl
Run the demo program based on python API
Prepare model files
- Download model
wget http://paddle-inference-dist.bj.bcebos.com/mobilenet_v1.tar.gz
tar zxf mobilenet_v1.tar.gz
- Convert model with opt tool
paddle_lite_opt --model_dir=./mobilenet_v1 \
--optimize_out=mobilenet_v1_opt \
--optimize_out_type=naive_buffer \
--valid_targets=arm
Successful conversion
Run the model
It should be noted that there are two demo files here, the difference between them is
full_api.py
The model file needed in the file is the__model__
and__param__
file, and the detailed API: CxxPredictorlight_api.py
The model file needed in opt is themodel.nb
file after opt conversion . Detailed API: LightPredictor
# light api的输入为优化后模型文件mobilenet_v1_opt.nb
python3 mobilenetv1_light_api.py --model_dir=mobilenet_v1_opt.nb
Deploy your own model
The model used by Paddle for reasoning is save_inference_model
saved through this API. There are two formats for saving. Here, the model parameter file generated by running on AI studio is downloaded and mounted on the Raspberry Pi:
Two model formats
-
non-combined form : a separate file to save parameters, such as set
model_filename
toNone
,params_filename
toNone
-
combined form : the arguments on the same file, such as setting
model_filename
ismodel
,params_filename
asparams
Compile the opt tool
Compile on Raspberry Pi:
cd Paddle-Lite
./lite/tools/build.sh build_optimize_tool
Convert model using opt
paddle_lite_opt --model_dir=./mobilenet_v1 \
--valid_targets=arm \
--optimize_out_type=naive_buffer \
--optimize_out=mobilenet_v1_opt
Specific API details refer to:
Compilation process reference: