We are using OpenVINO R5 and trying to load the networks in the parent process and inference calls are made in the forked child.
The Infer() call is hanging in the child process. The same call works fine when performed in the parent process.
Is multiprocessing supported for OpenVINO models in C++?
I am also experiencing a related threading issue in a slightly different situation than yours. Mine is around Infer request too. I think the best way to proceed would be if we prepare a minimal repro; just a few C++ lines code demonstrating the issue. Do you think you could provide such a minimal repro for your case? I am also working on mine ( ETA end of the week I hope) that I believe is related but cannot be 100% sure.