I am trying to run yolov3 model on VPU cores with the help of HDDL plugin. I am using object_detection_demo_yolov3_async application but i am getting 1.5-2 FPS which is very bad. As per the device_snapshot and utilization log, vpu cores are not being utilized 100%. I have attached this log for reference.
I also tried with the benchmark application with yolov3 model and i got VPU cores utilization as 100% and throughput of 38 FPS.
Can you please tell me how benchmark application is using all vpu cores completely and giving far better throughput compared to object_detection_demo_yolov3_async and other applications?
And Do i need to modify anything in source code of these application in order to use vpu cores completely?
I apologize for the delay, the object_detection_demo_yolov3_async was not developed for HDDL and it only uses 2 infer requests (hard-coded). You should be able to modify the source code of the demo to use additional infer requests.
The following link contains programming guides for HDDL devices.