Open isra60 opened 2 years ago
After the build, you will need to manually copy onnxruntime_cxx_api.h and onnxruntime_c_api.h from the source dir to /usr/include or somewhere else.
And the shared libs to link against my c++ inference code?? Or are these ones??
libonnxruntime.so
libonnxruntime.so.1.10.0
Yes. And libonnxruntime_providers_shared.so, libonnxruntimeproviders*.so if they exist.
This issue has been automatically marked as stale due to inactivity and will be closed in 7 days if no further activity occurs. If further support is needed, please provide an update and/or more details.
Hi there,
Had the same issues here, the problem was that after the build a sudo make install
in the build\Linux\Release\
folder has to be run. This is not in the documentation anywhere, no clue why but hope this fixes other peoples problems.
Describe the bug I have a Jetson Xavier NX and I want to use the c++ API of the onnxruntime, so instead of using the standard wheel from the Jetson Model Zoo (https://elinux.org/Jetson_Zoo#ONNX_Runtime) I need to build the entire onnxruntime again with the option of build the shared libs
As reference I'm using this tutorial https://onnxruntime.ai/docs/build/eps.html#nvidia-jetson-tx1tx2nanoxavier
System information Jetpack 4.6 L4T
To Reproduce This is my command line to build onnxruntime Note the use of --build_shared_lib which I think is the proper way to obtain the include and libs for the c++ API
After the long building, I have a path like this onnxruntime/build/Linux/Release but in that folder I don't found any reference to the C++ API I mean something like include/onnxruntime/core/session/onnxruntime_cxx_api.h
Also, do you know if the wheel provided by NVIDIA is built with the TensorRT option??