Contributor
Regular ContributorHi Ruben,
I think you might need to try out with OpenVINO example design or other runtime example design to see if it is working from your side (eg. classification_sample_async or object_detection_demo)?
ContributorHello @JohnT_Intel ,
Both examples work, but they are intended for CPU/GPU. In addition, they collect multiple input images into a batch and request inference for the entire batch just like the benchmark example. The issue is related to FPGA DLA instantiation. I need to request an inference on every input event. For some reason, this creates a new DLA instance each time instead of reusing the existing one. This leads to an error once the number of inferences reaches five. Do you have any suggestions to address this?
