These compile errors came out from 'BERT' demo about tensorrt HOT 8 CLOSED

I fixed the original problem by adding c++11 flags in demo/BERT/CMakeLists.txt

cmake_minimum_required(VERSION 3.8 FATAL_ERROR)
project(cmake_and_cuda LANGUAGES CXX CUDA)
 
add_compile_options(-std=c++11)

...

from tensorrt.

@ginn24
sudo ln -s TensorRT-5.1.5.0/lib/libnvinfer.so /usr/lib/libnvinfer.so

from tensorrt.

Could you share the procedure to see this output?

I could build this with the following steps. (ubuntu)
$ git clone -b release/5.1 https://github.com/nvidia/TensorRT TensorRT
$ cd TensorRT
$ git submodule update --init --recursive
$ export TRT_SOURCE=pwd
$ docker build -f docker/ubuntu-18.04.Dockerfile --build-arg CUDA_VERSION=10.1 --tag=tensorrt .
$ docker run --rm -ti --runtime=nvidia tensorrt
(docker)# git clone -b release/5.1 https://github.com/nvidia/TensorRT TensorRT
(docker)# cd TensorRT
(docker)# git submodule update --init --recursive
(docker)# export TRT_SOURCE=pwd
(docker)# mkdir -p TensorRT/demo/BERT/build
(docker)# cd TensorRT/demo/BERT/build
(docker)# cmake ..
(docker)# make -j

from tensorrt.

@haanjack Thank you. However, there are some problems.

1. The same error came out when I changed the docker build option to ubuntu-16.04 + Cuda 10.0 or centos-7. + Cuda 10.0

2. That error came out when I installed CUDA 10.1 and changed build option to ubuntu 18.04 and CUDA 10.1

/usr/bin/ld: cannot find -lnvinfer
collect2: error: ld returned 1 exit status
CMakeFiles/sample_bert.dir/build.make:85: recipe for target 'sample_bert' failed
make[2]: *** [sample_bert] Error 1
CMakeFiles/Makefile2:73: recipe for target 'CMakeFiles/sample_bert.dir/all' failed
make[1]: *** [CMakeFiles/sample_bert.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2

from tensorrt.

You can install TensorRT and set LD_LIBRARY_PATH.
https://blog.csdn.net/zong596568821xp/article/details/86077553

from tensorrt.

@sboschang I've already installed TensorRT but to install OSS component makes some error

from tensorrt.

The original error seems to be missing c++11 flags? I have the same error.

from tensorrt.

Warnings and errors look like missing C++11 flag, @Meteorix's solution looks right to me.

from tensorrt.