Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

NSC2 is slower than CPU

TA1
Beginner
704 Views

Hello 

I'm beginner , sorry for poor English 

I got similar (NCS2 was much slower than CPU)results, but not demo models.

I made a deep learnning models which predict MNIST, and then converted frozen .pb file to IR format(.bin .xml) and inferred using OpenVINO for test.

Does it depend on complexity of model(Is MNISTso simple that NCS2 accellate?)?

 SPEC bellw:

python 3.6.8

OpenVINO 2021.2

Tensorflow 2.4.0

Windows 10

Intel(R) Core(TM) i5-7200U CPU @ 2.50GHz 

 

TAIKI

0 Kudos
4 Replies
Sebastian_M_Intel
Moderator
693 Views

Hello TA1, 

 

Thank you for posting on the Intel® communities. 

 

We would like to inform you that we have a forum for these specific issues and products, so we are moving it to the "Intel® Distribution of OpenVINO™ Toolkit" forum so you can get better support for this matter. 

https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/bd-p/distribution-openvino-toolkit  

 

Best regards, 

 

Sebastian M 

Intel Customer Support Technician 

0 Kudos
Munesh_Intel
Moderator
674 Views

Hi Taiki,

Thanks for reaching out to us.

Measuring inference performance involves many variables and is extremely use-case and application dependent. Intel uses four parameters for measurements, which are key elements to consider for a successful deep learning inference application, as follows:

  1. Throughput 
  2. Value 
  3. Efficiency 
  4. Latency 


As you can see in the performance benchmark page, for throughput comparison, NCS2 performance is better than Intel Atom® x5-E3940 processor, but is lesser than Intel® Core™ processors.


Regards,

Munesh


0 Kudos
Munesh_Intel
Moderator
637 Views

Hi Taiki,

This thread will no longer be monitored since we have provided references. If you need any additional information from Intel, please submit a new question.


Regards,

Munesh


TA1
Beginner
629 Views

Hi, Munesh s

Thank you.

Regards,

Munesh

0 Kudos
Reply