how can i run onnxruntime C++ api in Jetson OS ?
TensorRT Version: 10.3
GPU Type: Jetson
Nvidia Driver Version:
CUDA Version: 8.0
Operating System + Version: Jetson Nano
Baremetal or Container (if container which image + tag): Jetpack 4.6
i installed python onnx_runtime library but also i want to run in onnx_runtime in c++ api.
so how can i build onnx_runtime c++ api? (there are no documents about this problem…]
Request you to share the ONNX model and the script if not shared already so that we can assist you better.
Alongside you can try few things:
- validating your model with the below snippet
filename = yourONNXmodel
model = onnx.load(filename)
2) Try running your model with trtexec command.
In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
i just want to know how i can build onnx library and use <onnxruntime_cxx_api.h> in jetson board.
We are moving this post to Jetson forum to get better help.
You can find the prebuilt package for Jetson on the below link directly.
The onnxruntime *.so will be installed after the pip3 command:
$ find / -iname libonnxruntime*
i have the same problem: try to load ONNX model on jetson, i did as this answer and found libonnxruntime_providers_cuda.so, libonnxruntime_providers_shared.so and libonnxruntime_providers_tensorrt.so as you said. However i still am missing appropriate libonnxruntime.so and libonnxruntime.so.1.12.0 and also onnxruntime_c_api.h
where can I find them?
P/s: i found on the release page of ONNX : [onnxruntime-linux-aarch64-1.11.0.tgz], which works on jetson nano with all files but only CPU and very slow. any combination of this release and the files from the answer cause core dump error
Please help to open a new topic. Thanks