tensorrt之tensorrtx编译：遇到的错误提示

一、tensorrtx

编译步骤：

mkdir build
cd build
cmake ..
make                         // /workspace/tensorrt_release/include# cp -r NvInfer.h /usr/local/include/tensorrt/ ***
sudo ./yolov5 -s             // serialize model to plan file i.e. 'yolov5s.engine'
sudo ./yolov5 -d  ../samples // deserialize plan file and run inference, the images in samples will be processed.

make时遇到问题：

CMake Error: The current CMakeCache.txt directory /workspace/tensorrtx/yolov5/build/CMakeCache.txt is different than the directory /home/zbsj2/projects/deploy/tensorrtx/yolov5/build where CMakeCache.txt was created. This may result in binaries being created in the wrong place. If you are not sure, reedit the CMakeCache.txt

CMakeCache.txt之前编译时留下的缓存，应该把build删掉重新mdir build 编译。

 

二、tensorrtx

make时：

/workspace/tensorrtx/yolov5/yololayer.h:6:10: fatal error: NvInfer.h: No such file or directory
 #include "NvInfer.h"

需要把tensorrt release版本下的include添加到系统环境变量

/workspace/tensorrt_release/include# cp -r NvInfer.h /usr/local/include/tensorrt/

三、tensorrtx

make时：

Linking CXX shared library libmyplugins.so
/usr/bin/ld: cannot find -lnvinfer
collect2: error: ld returned 1 exit status

问题：系统环境变量缺少对应的lib

/workspace/tensorrt_release/lib# cp -r libnvinfer.so /usr/local/lib

四、tensorrtx编译完产物：

 

得到生成的 libmyplugins.so yolov5

五、yolov5s.engine

执行命令sudo ./yolov5 -s 时报错：./yolov5: error while loading shared libraries: libmyelin.so.1: cannot open shared object file: No such file or directory

同样的道理，没有把对应的静态库添加到系统环境变量

解决：cp lib

得到产物yolov5s.engine：

六、images

执行 sudo ./yolov5 -d  ../samples 时得到检测后的两张图 时：

报错：read_files_in_dir failed.

解决：将原图目录samples 放到build 同级目录。

七、mnist例子

跑tensorrt_release 下面的mnist例子

报错：

root@65c48c6dc77c:/workspace/tensorrt_release/data/mnist# python3 ./download_pgms.py
Traceback (most recent call last):
  File "./download_pgms.py", line 2, in <module>
    from PIL import Image
ModuleNotFoundError: No module named 'PIL'

解决：pip install pillow

通过运行生成的 sample_mnist 文件就可以测试TensorRT是否正确的编译安装了。但是运行前需要先下载mnist数据。完成的操作如下：

# 进入下载mnist数据脚本所在的目录
cd $TRT_RELEASE/data/mnist

# 运行下载mnist数据的脚本
python3 ./download_pgms.py

# 进入sample_mnist 所在的目录
cd $TRT_RELEASE/bin

# 运行sample_mnist
./sample_onnx_mnist

如下图所示：