我压根编译的时候没选rt
PS E:\projects\seg\cpp\building\Release> .\test_seg.exe --model_dir=./pp_liteseg_infer_model --img_path=./cityscapes_demo.png --devices=GPU
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0721 00:00:41.031344 7692 tensorrt.cc:56] You are using Paddle compiled with TensorRT, but TensorRT dynamic library is not found. Ignore this if TensorRT is not needed.
The TensorRT that Paddle depends on is not configured correctly.
Suggestions:
- Check if the TensorRT is installed correctly and its version is matched with paddlepaddle you installed.
- Configure environment variables as follows:
- Linux: set LD_LIBRARY_PATH by
export LD_LIBRARY_PATH=... - Windows: set PATH by
set PATH=XXX;%PATH% - Mac: set DYLD_LIBRARY_PATH by
export DYLD_LIBRARY_PATH=...
4条答案
按热度按时间pcww981p1#
paddle包是自己编译的还是下载已经编译好的呢？如果是自己编译的，编译选项-DWITH_TENSORRT，可选择是否选择TRT，具体可参考https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/install/Tables.html#Compile；
ipakzgxi2#
paddle包是自己编译的还是下载已经编译好的呢？如果是自己编译的，编译选项-DWITH_TENSORRT，可选择是否选择TRT，具体可参考https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/install/Tables.html#Compile；
是官网下载的的cuda11.2的但是我没用tr，这也不能阻止程序运行吧
yhxst69z3#
https://www.paddlepaddle.org.cn/inference/master/guides/install/download_lib.html#linux 可以安装这个试试
wn9m85ua4#
https://www.paddlepaddle.org.cn/inference/master/guides/install/download_lib.html#linux 可以安装这个试试
非常感谢大佬！成功了！虽然我下载的windows的2.5版本