Interested in a basic-basic-basic Visual Studio (C++) example for windows that is fairly self-contained (only uses inference_library.lib and the necessary plugin library) and can read local .bin/.xml IR files to implement a neural network. Seems like all the demos have LOTS of dependencies on paths, extra libraries, python scripts - and not in a good way.
Are there examples like this? If so, where?
I don't understand why. This seems like the most basic of tutorials that would help adoption of this framework. I have not seen a lot of simple examples available, and am not sure why I am having the problems I am having. A simple 'ground truth' application might go a LONG way to answering key questions. I am positive I am not alone in this request.
Dear Rob, have you taken a look at the open source version of OpenVino here ?
OpenVino does officially support CMake integration. So if you would like to write your own application you simply need to create a CMake project and just call find_package(InferenceEngine) inside (similarly how it's done for the samples). And in this case all the includes and libraries are available by InferenceEngine_INCLUDE and _LIBRARIES correspondingly. But even in this case the OpenVino application writer should configure InferenceEngine_DIR accordingly (pointing to the folder with InferenceEngineConfig.cmake). The steps are actually described in the following page of our open source repo (“Adding to your project” section):
Hope it helps and thanks for using OpenVino !