Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
154 Views

Opencv vs inference_engine performance

Hello

Im on a rpi 3b doing some test on face tracking, im using face-detection-adas-0001 model and python.

I have a test using openCv and another one using inference_engine, and on the openCv version get almost double fps(7.7 fps vs 4.5fps) is that difference in performance correct? Is there any way of optimizing to get more fps?

Thanks!

0 Kudos
6 Replies
Highlighted
154 Views

Hi Ignacio,

The overall frame rate for Inference engine is rather determined only by the slowest part of the pipeline (decoding IR inference) and not by the sum of the stages which includes latency in capturing input frames.

However you may try improving the performance by using Inference Engine Async API.

Best Regards,

Surya

0 Kudos
Highlighted
154 Views

Hi

Yes i tried and performance increased, but also make opencv async.... so ended in the same situation, opencv seems faster.

That seems extrange to me as i expected inference engine to be faster, thats why im asking

0 Kudos
Highlighted
154 Views

Note: im trying to post another question but not able to do it, i allways get "The form has become outdated." error msg, tried two different browsers

0 Kudos
Highlighted
154 Views

Hi Ignacio,

Can you please share with us the codes, commands and necessary files that you are using to load the model and inferencing using OpenCV and OpenVINO.

Best Regards,

Surya

0 Kudos
Highlighted
154 Views

Thank you for taking a look!!

Attached files, async version in inference engine and openCv version.

 

 

0 Kudos
Highlighted
154 Views

Hi Ignacio,

We don't have any public benchmarks between OpenVINO and OpenCV. However you may try optimizing the OpenVINO Inference engine using techniques given at smart video workshop.

Best Regards,

Surya

0 Kudos