Performance of NCS Sticks and OpenVino

[idata]

I have been using the NCS 1 compute stick for some time now.

I installed OpenVino version 2018 4.420 on my older i5 Ivy Bride 1.7ghz 6GB DDR3

memory laptop with a single USB 3 port running windows 10.

The Demo Security Barrier Camera with no NCS sticks ran at 29ms ~ 34fps

The vehicle detection time was 11.8 ms

So I was looking forward to even better performance and much to my shock

with one NCS2 and one NCS1 I got ~10 fps.Unbelievable, the CPU only version ran 300% faster.Total time was 95.57ms ~ 10fpsThe total vehicle detection time was 81.86 ms

With just the NCS 1 plugged in the performance was a bit worse 107.28ms ~ 9fps

Vehicle detection time was better 78.9ms ~ 12fps

With just the NCS 2 plugged in the performance was a bit worse 107.8ms ~ 9fps

Vehicle detection time was better 86.29ms ~ 11.7fps

Proving newer is not always better? I am totally perplexed by the results. I expected the NCS 2 to outperform the NCS 1 because of the additional shave cores intead the NCS 2 performed worse.

Movidius any explanations? And why is my OLD i5 cpu performing 800% better with vehicle detection.Is there something wrong with the demo code and MYRIAD?

[idata]

I will link each other.

https://software.intel.com/en-us/forums/computer-vision/topic/801128

Thank you. Bob.

[idata]

So PINTO .what i am seeing is expected? A single 5 year old I5 CPU runs rings around TWO MOVIDIUS sticks? Have a hard time understanding that. The cpu is general purpose. The graph for movidus dropped down to fp16. What's the bottle neck. Or are the sticks that slow

[idata]

@chicagobob123

I do not know the internal implementation of OpenVINO, so I can not say exactly.

https://ark.intel.com/ja/products/65707/Intel-Core-i5-3317U-Processor-3M-Cache-up-to-2-60-GHz-

When using the CPU, I think that 2 Core + 4 Thread is utilized to the maximum.

My memory is ambiguous, OpenVINO seems to be using an API similar to NCSDK internally.In other words, when using NCS, it always seems to be running in one thread.

I abandoned any implementation that already used NCS.

Sadly, I feel that development using NCS is barren until OpenVINO is compatible with ARM.

[idata]

ARM is coming soon. So do not toss the Pi just yet :smile:

[idata]

@chicagobob123

Yes, I know.

I am looking forward to. :) https://github.com/opencv/dldt/issues/3

[idata]

Did you download opevino 5 for the pie?

[idata]

@chicagobob123

Did you download opevino 5 for the pie?

I downloaded it and installed it.

And it is operating normally.It's the best!!I plan to update my repository during today or tomorrow.https://github.com/PINTO0309/MobileNet-SSD-RealSense.githttps://software.intel.com/en-us/articles/OpenVINO-Install-RaspberryPI$ sudo apt update $ sudo apt upgrade $ wget https://drive.google.com/open?id=1rBl_3kU4gsx-x2NG2I5uIhvA3fPqm8uE -o l_openvino_toolkit_ie_p_2018.5.445.tgz $ tar -zxf l_openvino_toolkit_ie_p_2018.5.445.tgz $ rm l_openvino_toolkit_ie_p_2018.5.445.tgz