Error: floating constant is out of range

[erfaneshratifar]

Hi,

I'm getting this error while building:

YoLov5-TensorRT-NMS/yololayer.h(78): warning: function "nvinfer1::IPluginV2Ext::configurePlugin(const nvinfer1::Dims *, int32_t, const nvinfer1::Dims *, int32_t, const nvinfer1::DataType *, const nvinfer1::DataType *, const __nv_bool *, const __nv_bool *, nvinfer1::PluginFormat, int32_t)" is hidden by "nvinfer1::YoloLayerPlugin::configurePlugin" -- virtual function override intended?

/usr/include/c++/9/limits(1715): error: floating constant is out of range

1 error detected in the compilation of "YoLov5-TensorRT-NMS/yololayer.cu".
CMake Error at yoloplugin_generated_yololayer.cu.o.Debug.cmake:280 (message):
  Error generating file
  YoLov5-TensorRT-NMS/build/CMakeFiles/yoloplugin.dir//./yoloplugin_generated_yololayer.cu.o


make[2]: *** [CMakeFiles/yoloplugin.dir/build.make:364: CMakeFiles/yoloplugin.dir/yoloplugin_generated_yololayer.cu.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:110: CMakeFiles/yoloplugin.dir/all] Error 2
make: *** [Makefile:91: all] Error 2

[upczww]

What's your build env? gcc, nvcc, tensorrt, cuda version?

[erfaneshratifar]

CUDA 11.3

TensorRT: 7.2.3-1+cuda11.1

GCC 9.3.0

NVCC: nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Sun_Mar_21_19:15:46_PDT_2021 Cuda compilation tools, release 11.3, V11.3.58 Build cuda_11.3.r11.3/compiler.29745058_0

[upczww]

You can try docker image nvcr.io/nvidia/tensorrt:21.06-py3

[upczww]

remember to install opencv

apt update

apt install libopencv-dev

[erfaneshratifar]

Thanks, libopencv-dev solved the issue.

[wuqingzhou828]

What's your build env? gcc, nvcc, tensorrt, cuda version?

我遇到一样的问题 安装了libopencv-dev还是报一样的错误 谢谢 环境： tensorRT 8.0.3-1+cuda11.3 nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Sun_Aug_15_21:14:11_PDT_2021 Cuda compilation tools, release 11.4, V11.4.120 Build cuda_11.4.r11.4/compiler.30300941_0

[wuqingzhou828]

What's your build env? gcc, nvcc, tensorrt, cuda version?

我遇到的问题

yololayer.cu(260): error: declaration is incompatible with "int nvinfer1::YoloLayerPlugin::enqueue(int, const void *const *, void *const *, void *, cudaStream_t)" 安装了libopencv-dev还是报一样的错误 谢谢 环境： tensorRT 8.0.3-1+cuda11.3 nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Sun_Aug_15_21:14:11_PDT_2021 Cuda compilation tools, release 11.4, V11.4.120 Build cuda_11.4.r11.4/compiler.30300941_0