Community
cancel
Showing results for 
Search instead for 
Did you mean: 
muntakimrafi
Beginner
94 Views

Openvino Benchmark Performance

Jump to solution

Hello,

I am using Openvino to benchmark an edge device that I was given from my lab for research purposes. It has a CPU and a VPU to accelerate inference of AI applications. 

I am supposed to use the openvino python benchmark application to measure the throughput and latency of the device.

But while running the benchmark application, I saw that the numbers I am getting are a lot less than the performance mentioned here.

https://docs.openvinotoolkit.org/latest/openvino_docs_performance_benchmarks.html

I am using model weights made available by openvino model zoo to make sure there is nothing wrong in the model conversion part. 

 

Did someone face this irregularity in the numbers presented in the openvino performance benchmark link provided above? 

 

Thanks in advance. 

0 Kudos

Accepted Solutions
IntelSupport
Community Manager
76 Views

 Hello Muntakimrafi,

Thanks for reaching out.

All the performance measure has been done and validated multiple platforms listed in the documentation. For the full platform configuration details, check out this documentation.

 

Also, feel free to share your hardware details, model name, and your result for us to check on our part.

 

Regards,

Aznie


View solution in original post

2 Replies
IntelSupport
Community Manager
77 Views

 Hello Muntakimrafi,

Thanks for reaching out.

All the performance measure has been done and validated multiple platforms listed in the documentation. For the full platform configuration details, check out this documentation.

 

Also, feel free to share your hardware details, model name, and your result for us to check on our part.

 

Regards,

Aznie


View solution in original post

IntelSupport
Community Manager
51 Views

Hi Muntakimrafi,

Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored. 


Regards,

Aznie