Jetson执行目标检测模型PPYOLOE测试代码报错libfastdeploy.so: undefined reference to `paddle2onnx::Export

温馨提示：根据社区不完全统计，按照模板提问，可以加快回复和解决问题的速度

环境

• 【FastDeploy版本】： 说明具体的版本，如fastdeploy-linux-gpu-1.0.6
• 【编译命令】如果您是自行编译的FastDeploy，请说明您的编译方式（参数命令）
• 【系统平台】: Linux x64(Ubuntu 18.04)
• 【硬件】： Jetson 4.6.1， CUDA 10.2 CUDNN 8.2.1.32
• 【编译语言】： C++

C++部署
确认开发环境已准备FastDeploy C++部署库，参考FastDeploy安装安装预编译的FastDeploy，或根据自己需求进行编译安装。

本文档以PaddleDetection目标检测模型PPYOLOE为例展示CPU上的推理示例：
假设当前目录已经准备好infer_demo.cc和CMakeLists.txt两个文件，即可进行编译

Linux & Mac
打开命令行终端，进入infer_demo.cc和CmakeLists.txt所在的目录，执行如下命令

mkdir build & cd build
cmake ..
make -j
执行make -j时候，报错
(fastdeploy) nvidia@nx:~/FastDeploy/test_demo/build$ make -j
[ 50%] Building CXX object CMakeFiles/infer_demo.dir/infer_demo.cc.o
[100%] Linking CXX executable infer_demo
/home/nvidia/FastDeploy/build/installed_fastdeploy/lib/libfastdeploy.so: undefined reference to paddle2onnx::Export(void const*, long, void const*, long, char**, int*, int, bool, bool, bool, bool, bool, paddle2onnx::CustomOp*, int, char const*, char**, int*, char const*, bool*, bool)' /home/nvidia/FastDeploy/build/installed_fastdeploy/lib/libfastdeploy.so: undefined reference to paddle2onnx::ConvertFP32ToFP16(char const*, int, char**, int*)'
collect2: error: ld returned 1 exit status
CMakeFiles/infer_demo.dir/build.make:119: recipe for target 'infer_demo' failed
make[2]: *** [infer_demo] Error 1
CMakeFiles/Makefile2:109: recipe for target 'CMakeFiles/infer_demo.dir/all' failed
make[1]: *** [CMakeFiles/infer_demo.dir/all] Error 2
Makefile:90: recipe for target 'all' failed
make: *** [all] Error 2

Start with infer_demo.cc and CMakeLists.txt, then reproduce the failure using cmake .. and make -j on the Jetson environment described. Inspect how libfastdeploy.so is linked and how the paddle2onnx symbols are supplied. Done means the PPYOLOE test executable links successfully without the reported undefined references.