dingidng
commented
1 year ago 这个问题我遇到过：记录下来你试试能不能解决你的问题
简约版（省流） 在激活后执行export LD_LIBRARY_PATH="$CONDA_PREFIX/lib"将包括libcudart.so.11.0如果你想让它自动化，将此内容添加到env-prefix/etc/conda/activate.d/env_vars.sh，这将在conda activate上运行脚本并设置LD_LIBRARY_PATH
Linux和Windows系统下:安装Anaconda、Paddle、tensorflow、pytorch，GPU[cuda、cudnn]、CPU安装教学,以及查看CPU、GPU内存使用情况
错误log如下，我的cuda环境时10.2.89，这个cuda版本不能更换，请问下作者，怎么适配10.2.89的cuda？谢谢
root@e49e02585200:/home/FastDeploy/python_demo# python3 paddledetection.py Traceback (most recent call last): File "/usr/local/lib/python3.7/site-packages/fastdeploy/c_lib_wrap.py", line 164, in
from .libs.fastdeploy_main import *
ImportError: libcudart.so.11.0: cannot open shared object file: No such file or directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "paddledetection.py", line 3, in
import fastdeploy.vision as vision
File "/usr/local/lib/python3.7/site-packages/fastdeploy/init.py", line 122, in
from .c_lib_wrap import (
File "/usr/local/lib/python3.7/site-packages/fastdeploy/c_lib_wrap.py", line 166, in
raise RuntimeError(f"FastDeploy initalized failed! Error: {e}")
RuntimeError: FastDeploy initalized failed! Error: libcudart.so.11.0: cannot open shared object file: No such file or directory