mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
e24c592f43
* Update paddle_inference.cmake * Update process_libraries.py.in * Update process_libraries.py.in * Update paddle_inference.cmake * Update CMakeLists.txt * Update VERSION_NUMBER * Update VERSION_NUMBER * Update download_prebuilt_libraries.md * Update gpu.md * Update cpu.md * Update download_prebuilt_libraries.md * Update jetson.md * Update tensorrt_tricks.md * Update cpp.md Co-authored-by: Jason <jiangjiajun@baidu.com>
1.2 KiB
1.2 KiB
Jetson部署库编译
FastDeploy当前在Jetson仅支持ONNX Runtime CPU和TensorRT GPU两种后端推理
C++ SDK编译安装
编译需满足
- gcc/g++ >= 5.4(推荐8.2)
- cmake >= 3.10.0
- jetpack >= 4.6.1
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy
mkdir build && cd build
cmake .. -DBUILD_ON_JETSON=ON \
-DENABLE_VISION=ON \
-DCMAKE_INSTALL_PREFIX=${PWD}/installed_fastdeploy
make -j8
make install
编译完成后，即在CMAKE_INSTALL_PREFIX指定的目录下生成C++推理库
Python编译安装
编译过程同样需要满足
- gcc/g++ >= 5.4(推荐8.2)
- cmake >= 3.10.0
- jetpack >= 4.6.1
- python >= 3.6
所有编译选项通过环境变量导入
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/python
export BUILD_ON_JETSON=ON
export ENABLE_VISION=ON
python setup.py build
python setup.py bdist_wheel
编译完成即会在FastDeploy/python/dist目录下生成编译后的wheel包，直接pip install即可
编译过程中，如若修改编译参数，为避免带来缓存影响，可删除FastDeploy/python目录下的build和.setuptools-cmake-build两个子目录后再重新编译