marcoslucianops / DeepStream-Yolo

NVIDIA DeepStream SDK 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
MIT License
1.38k stars 343 forks source link

/usr/include/x86_64-linux-gnu/NvInferRuntimeCommon.h:19:10: fatal error: cuda_runtime_api.h: No such file or directory #489

Closed senhorinfinito closed 7 months ago

senhorinfinito commented 7 months ago

CUDA_VER=12.1 make -C nvdsinfer_custom_impl_Yolo

while converting the yolov8 got the following error

make: Entering directory '/opt/nvidia/deepstream/deepstream-6.3/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo'
g++ -c  -o yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-12.1/include yolo.cpp
In file included from /usr/include/x86_64-linux-gnu/NvInferLegacyDims.h:16,
                 from /usr/include/x86_64-linux-gnu/NvInfer.h:16,
                 from /usr/include/x86_64-linux-gnu/NvOnnxParser.h:26,
                 from yolo.cpp:26:
/usr/include/x86_64-linux-gnu/NvInferRuntimeCommon.h:19:10: fatal error: cuda_runtime_api.h: No such file or directory
   19 | #include <cuda_runtime_api.h>
      |          ^~~~~~~~~~~~~~~~~~~~
compilation terminated.
make: *** [Makefile:81: yolo.o] Error 1
make: Leaving directory '/opt/nvidia/deepstream/dee
marcoslucianops commented 7 months ago

Did you install the requirements following the https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/dGPUInstalation.md doc?

senhorinfinito commented 7 months ago

Im using the nvcr.io/nvidia/deepstream:6.3-samples image

senhorinfinito commented 7 months ago

Also cuda version is 12.3 , driver 545.23.06 and

pip show tensorrt

Name: tensorrt
Version: 8.5.3.1
Summary: A high performance deep learning inference library
Home-page: https://developer.nvidia.com/tensorrt
Author: NVIDIA Corporation
Author-email: None
License: Proprietary
Location: /usr/lib/python3.8/dist-packages
Requires: 
Required-by: 
senhorinfinito commented 7 months ago

Can we get a docker file to convert the model ? @marcoslucianops

marcoslucianops commented 7 months ago

https://github.com/marcoslucianops/DeepStream-Yolo#docker-usage