search

enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
MIT License
1.19k stars 315 forks source link

[Cuda failure] no kernel image is available for execution on the device #13

Open anisghaoui opened 4 years ago

anisghaoui commented 4 years ago

Hi,

After executing the compiled binaries on Ubuntu, I hit this error :

Cuda failure: no kernel image is available for execution on the device in file /home/path/to//TensorRT/yolo-tensorrt/modules/plugin_factory.cpp at line 155 Aborted (core dumped) Any idea on why does it occur ?

Ubuntu 18.04 Cuda-10.2 TRT 7.5

wrennywang commented 4 years ago

修改CMakeLists.txt中显卡算力配置，与运行gpu算力一致，https://developer.nvidia.com/cuda-gpus

if(CUDA_VERSION_MAJOR GREATER 9) message("-- CUDA ${CUDA_VERSION_MAJOR} detected") set( CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS}; -gencode arch=compute_72,code=sm_72 ) endif()