A new C++ application was written to apply the inference to the frames captured from an image sensor ([https://cdn.sparkfun.com/datasheets/Sensors/LightImaging/OV5640_datasheet.pdf OV5640]) instead of images retrieved from files. Like version2version 2, inference run on NPU, so only the fully-quantized model was tested with the version 3 application.

Note that in with this caseimage sensor, the framerate frame rate is cappedat 30 fps.

TBD - "The first execution of model inference using the NN API always takes many times longer, because of model graph initialization needed by the GPU/ML module" - Profiling?