Jetson部署库编译安装后运行错误

• 【系统平台】: Ubuntu 18.04

• 【硬件】： Jetson NX，jetpack4.6 CUDA 10.2 CUDNN 8.2

• 【编译语言】： C++ / Python(3.8）
  按照https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/jetson.md在Jetson NX上以源码方式编译安装fastDeploy,安装成功，但是在python中运行出错。

• 【编译命令】

• 先编译C＋＋
  git clone https://github.com/PaddlePaddle/FastDeploy.git
  cd FastDeploy
  mkdir build && cd build
  cmake .. -DBUILD_ON_JETSON=ON
  -DENABLE_VISION=ON
  -DENABLE_PADDLE_BACKEND=OFF \ # 可选项，如若不需要Paddle Inference后端，可关闭
  -DPADDLEINFERENCE_DIRECTORY=/Download/paddle_inference_jetson
  -DCMAKE_INSTALL_PREFIX=${PWD}/installed_fastdeploy
  make -j8
  make install

• Python编译安装：
  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

wheel包安装成功。

测试代码：
import cv2
import fastdeploy.vision as vision

model = vision.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel",
"ppyoloe_crn_l_300e_coco/model.pdiparams",
"ppyoloe_crn_l_300e_coco/infer_cfg.yml")

im = cv2.imread("ppocr_img/imgs/14.jpg")
result = model.predict(im)
print(result)

错误提示：
Traceback (most recent call last):
File "/home/nvidia/miniconda3/envs/camera/lib/python3.8/site-packages/fastdeploy/c_lib_wrap.py", line 164, in
from .libs.fastdeploy_main import *
ModuleNotFoundError: No module named 'fastdeploy.libs.fastdeploy_main'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/nvidia/PycharmProjects/untitled/fastdeploy_demo.py", line 2, in
import fastdeploy.vision as vision
File "/home/nvidia/miniconda3/envs/camera/lib/python3.8/site-packages/fastdeploy/init.py", line 122, in
from .c_lib_wrap import (
File "/home/nvidia/miniconda3/envs/camera/lib/python3.8/site-packages/fastdeploy/c_lib_wrap.py", line 166, in
raise RuntimeError(f"FastDeploy initalized failed! Error: {e}")
RuntimeError: FastDeploy initalized failed! Error: No module named 'fastdeploy.libs.fastdeploy_main'

Process finished with exit code 1