Intel Neural Compute Stick 2 / Movidius AI Test

By: IPVM Team, Published on Nov 21, 2018

AI is a major trend in video surveillance with manufacturers paying significant attention to Intel's Movidius Myriad chips. Indeed, Avigilon has announced that their next generation AI H5 cameras will use the Myriad X.

But how well do these Myriad X chips perform?

IPVM has done its first testing of the Myriad X chip (via the NCS2) and shares results inside this report.

Intel / Movidius / Network Compute Stick Overview

Cameras like Avigilon will use Intel / Movidius chips inside them to deep learning / Artificial intelligence. To the side is an image of a Myriad X chip. Video will be sent into to on-board chip, the chip will run deep learning models and it will output categorizations of people, objects, faces, etc.

Just a week ago, Intel announced its second generation of 'Neural Compute Sticks' (NCS). While the first NCS had the original / older Movidius Myriad 2 chip, this new one has the newer Myriad X inside, which Intel claims "delivers 10X the performance compared to previous generations".

IPVM bought the NCS2 and tested it.

Areas Analyzed

Inside this report, we share results across:

  • Face detection using Intel's face-detection-retail-0004 model
  • Testing across Intel i7, Myriad 2 and Myriad X
  • FPS, CPU and RAM consumption variances across devices
  • Accuracy comparison of detection
  • YOLO support and issues

** ** * ***** trend ** ***** ************ with ************* ****** *********** attention ** *****'* ******** ****** *****. ******,******** *** ********* **** their **** ********** ** H5 *********** *** *** ****** X.

*** *** **** ** these ****** * ***** perform?

**** *** **** *** first ******* ** *** Myriad * **** (*** the ****) *** ****** results ****** **** ******.

Intel / ******** / ******* ******* ***** ********

******* **** ******** **** use ***** / ******** chips ****** **** ** deep ******** / ********** intelligence. ** *** **** is ** ***** ** a ****** * ****. Video **** ** **** **** to **-***** ****, *** chip **** *** **** learning ****** *** ** will ****** *************** ** people, *******, *****, ***.

**** * **** ***,***** ************ ****** ********** ** '****** ******* ******' (***). ***** *** first *** *** *** original / ***** ******** Myriad * ****, **** new *** *** *** newer****** * ******, ***** ***** ****** "delivers *** *** *********** compared ** ******** ***********".

**** ****** *** **** and ****** **.

Areas ********

****** **** ******, ** share ******* ******:

  • **** ********* ***** *****'* face-detection-retail-0004 *****
  • ******* ****** ***** **, Myriad * *** ****** X
  • ***, *** *** *** consumption ********* ****** *******
  • ******** ********** ** *********
  • **** ******* *** ******

[***************]

Key ********

*** *** ******** **** our ******* ***:

  • Myriad * ~= *.** ****** * ***: The NCS2 ran roughly 2.7x frames-per-second more than the NCS1 in their face detection model we tested. Intel says that different optimizations and measurement changes would increase this significantly (discussed in caveats below).
  • Faster **** *** (**): The NCS2 / Myriad X outperformed the i7-7700K (a top-of-the-line in 2017) chip tested here, a significant advance given the Myriad X being significantly lower cost and lower power consumption.
  • Little/no ******** ****: Our tests noted no differences in output video accuracy in line's feedback that OpenVINO's model-optimization step should be considered "lossless." They pointed out that allowing lossy model compression (when converting a model to be run on Myriad; eg FP32->FP16 data-type downsizing) would cause issues with vendors training a model with certain expectations, and having a different (lossy) model for inferring.
  • Model ************* ** ******: While Intel has mentioned YOLO support for OpenVino, the current YOLOv3 is not yet compatible on Myriad chips due to a particular network layer. ***** ************ **** ***** *** ******* converting ****** ** ** run ** ***, *** ****** is *** *** ********** on ****** ******* *** to * ********** ******* layer. 
    **** ** & **: Intel ******* ***** *** be *** ** ******, our *** ***** *******.
    **********+***: *** ***** ** this ****** **** *******, specifically ***** ****-*********-******-**** (********** light **** * ******-**** detector).
    *********+***: *** ***** *******. We **** ******* ****** models **** ****** ** Intel's *** ******.

*** ****** ***** ******** performance *******:

intel performance comparison2

Caveat ** *** / *****

***********, *****'* *** ******* are **** ****** **** our ***, *** **** reasons. **, *****'* ****-*********-******-**** model ******* *** *** ** CPU, **.* ** ******* (**** Intel ******** ********** ******* numbers ** **** ******).

* *** ****** ** our ***** ***** ******* out: (*) ** *** Python, **** ******* **** their *++ ****; (*) our ***-******* ******** ******* code (** ****** *******/******* frames), *** ********* ***** code; (*) ** *** not ***** ******* ************ handling ** ***** ***** loading, ***** ** ***** into ********.

Video **********

***** ** * ***** screencast **** ******* *** testing:

Questions / ******** / **** ** **** ****?

** **** ******* ******* of *** **** / Myriad * ***** **** other ********* *** **** more ****** **** *** next *** *****. **** would *** **** ** see ******?

Comments (12)

*'* **** ** ********** this **** ** * can ****. ** *** "plug" **** ***** **** a ******** *** *** a ******* *** *** camera ** ***** *********** objects? *** ***** ******** open ****** ** ******** for *********?

*** **** ****** ** into * *** **** like *** ***** *** device. ** * **********, these ****** ******* ****** aren't ****** *** ********** applications, *** *** **********/******* your ****** ******* / program ** *** ****** chip (** *** *** it ********, ****** *** compatible, ***). ***'** ** using ** ********** ****** chip ** *** **** world.

**** **** ** *** our **** ** *** repo ***** (*'** *** about ******* ** ****-****** license ** **), *** it's **** **** **** for ***. ***'** ** better ****** ******* ********'* own ****** *++ *****. You *** **** ***** (after *** ******* ********) at ~/*****/*******************/****************/****************/*******. ** ** "are **** **** ****** / ********", ** ******** guess is "***" - **** want ** *** *** started. *** ***'** **** to **** *** ******** license (**** ** *******) at ~/*****/*******************/*********.

**** ****** *** ****...

******* ********, *** ** talking $ ** $$ or $$$?

 

**** *** $***. ********** **********, *** ****'** *** back-order ********* 

****** **** **** **** them **-*****. * ******* one * **** *** and ** ** ******** ******. 

 

**** ******** - **** 622% *** *********** ** the **-***** **** **** each ********* *** ***** out ***** **** **** of ** ** ** it ******** ******* **** other ******?

 

****, *** *** *** the **** *** ****** testing?  ** ***** * significant ****** ** ******* on *** *****?  **** wondering **** *** ****** will ** ** *** cameras *******/****.

*** **** * ** all, *** *'* ************* myself. * ***** **'* as *** ******, ** considers ***% **** *********** of * **** *** of **'* * ***** (or ********** ********* ****** them). ** ************ *'* thinking ** **** *.**/* cores *****.

* ***** *** ***** now *** **** **, no ********** ****. *'** try ** ***** ** a ****** *** ** gauging. **** ***** ** a * *** *****, temperature ******* ** ****** X **** (** ***** rather **** *****) ******** to **** ****** ****.

* ***** **'* ** you ******, ** ********* 100% **** *********** ** 1 **** *** ** i7's * ***** (** comparable ********* ****** ****).

** **** ** ****** the ****, * ***** suggest **** *** ****** need ** ** ********** before ********, *.*. ***%=**%.

****** **** ******** *** 104%, ***** *** * has ** *****? ** it **** ***** ******** more **** *?

* *** **** ******* digging ** *** ******* portion.  ***** ** ** Intel *** ***** *** available *** ***(******* ****** Power).  **’* **** *** draw *** ****.  * am *** ******* *** it ******** ** *** TDP ** * ******** chip **** ** ******* as ** ******* *** industry ***** ** ******* this **** ** **** as ********... ** *** not **** ****.  * haven’t **** **** **** to **** ******* ** thermal **** ** **** Artpec *****.  **** ** how ****** * ******** to ***** ****** **********:

****** * - *.* watt ***

**-***** - ** **** TDP

**** ********* - *-** watt ***

****** ***** - ** to *** **** *** **** ** **** is ** *** *** that ******** **** *** server **** ********** ****** analytics *********

 

* *****’* **** **** to **** *** *******/******* info *** ****** ********** like ********** ** *****.  Apple ***** ** ******* everything **** ***.  * suspect **** *** *** 1 **** *** ******** back ******* ***** ** thermal ***********.

 

 

***, ** *** ***** to ** *** / introductory ******** ** ** / **** ******** ** the **** ****** ** well. 

** *** **** ******* to ** ********* ***, rightfully **, **** *** not **** **** ***** / ******** ********* ****. Upcoming ********* **** ******* that.

****** ************ ******** **** help ** ********** *** concept ******.

* ****** * **** of ***** ** **** with **** ****** ** the ****** ****** ************ and *** **** ** play **** **** **** the *******. ** ******* 7 *** ******** **** SDK ***** *** *** OS **** *** ********* the ***** ** ***(*** driver). ******* ** ********** it *** ** ****** but *** ** **** as ******.

(** *** ** * can ****, *** "***" choice ** **** *** intel ***'* *** ******, etc.)

* ** ************* ** C++, **** ******* *******, but *** ******* **** pretty ****.

* **** **** ******** the ******* *** ******* them ** *** ******* line ** *** **** performance ** ****. ** is **** ** ********** the *** *** ****** feed **** ***** *** the ****** **** *** on ***********. *** *** license ***** ***** *** output ** ********* **** is *** **** *** license ***** ********* ***** is *** **** *** license ***** ***********. **** make * *********** ******* detection *** ***********.

** ***, ****** ************ with ***********, *** ** is ****** ***** ** even ***** ***.

 

 

 

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports

AI Video Tester Released on Apr 02, 2019
IPVM has released the world's first AI video tester that lets you see how various AI models (including from Amazon, Google, Microsoft and YOLO)...
Axis ARTPEC-7 Chip Release Examined on Apr 08, 2019
For years, Axis essentially de-promoted their own chips. Now, they are reversing course. Axis has announced ARTPEC-7, their latest chip, which...
Facial Recognition Systems Fail Simple Liveness Detection Test on May 17, 2019
Facial recognition is being widely promoted as a solution to physical access control but we were able to simply spoof 3 systems because they had no...
Carnegie Mellon AI Startup Zensors Profile on Jun 11, 2019
Zensors is a startup formed by Carnegie Mellon graduates from a Carnegie Mellon research project, offering customized models per camera that they...
UK Facial Recognition Essex Errors Report on Jul 05, 2019
Facial recognition trials in the UK have generated significant controversy and debate over the past few years. This week, it flared again when Sky...
Verkada People And Face Analytics Tested on Aug 16, 2019
This week, Verkada released "People Analytics", including face analytics that they describe is a "game-changing feature" that "pushes the...
Paravision AI Face Recognition Company Profile on Nov 01, 2019
Paravision (formerly EverAI) toutes being #1 in NIST testing and "America's only mission-critical face recognition" provider. We spoke to...
Ultinous European Analytics Startup Company Profile on Dec 04, 2019
European analytics-startup Ultinous pitches customers to "Have your own video analysis service!" We spoke to Ultinous to better understand their...
Ipsotek UK Video Analytics Company Profile on Jan 08, 2020
UK-based Ipsotek is one of just a few surviving independent video analytic developers from the 2000s. We covered them back in 2011 when they first...
Avigilon Facial Recognition 'Appearance Alerts' Tested on Dec 18, 2019
Avigilon has released 'Appearance Alerts' in ACC 7.4, which adds real-time facial recognition. To see how this performed, we tested them with...

Most Recent Industry Reports

Favorite Video Analytic Manufacturers 2020 on Feb 25, 2020
Video analytics is now as hot as ever, driven by the excitement of advancing deep learning offers. But what are actually integrator's...
Latest London Police Facial Recognition Suffers Serious Issues on Feb 24, 2020
On February 20, IPVM visited another live face rec deployment by London police, but this time the system was thwarted by technical problems and...
Masks Cause Major Facial Recognition Problems on Feb 24, 2020
Coronavirus is spurring an increase in the use of medical masks, which new IPVM test results show cause major problems for facial recognition...
Every VMS Will Become a VSaaS on Feb 21, 2020
VMS is ending. Soon every VMS will be a VSaaS. Competitive dynamics will be redrawn. What does this mean? VMS Historically...
Video Surveillance 101 Course - Last Chance on Feb 20, 2020
This is the last chance to join IPVM's first Video Surveillance 101 course, designed to help those new to the industry to quickly understand the...
Vulnerability Directory For Access Credentials on Feb 20, 2020
Knowing which access credentials are insecure can be difficult to see, especially because most look and feel the same. Even insecure 125 kHz...
AI/Smart Camera Tutorial on Feb 20, 2020
Cameras with video analytics, sometimes called 'Smart' camera or 'AI' cameras, etc. are one of the most promising growth areas of video...
China Manufacturer Suffers Coronavirus Scare on Feb 20, 2020
Uniview suffered a significant health scare last week after one of its employees reported a fever and initially tested positive for coronavirus....
Cheap Camera Problems at Night on Feb 19, 2020
Cheap cameras generally have problems at night, despite the common perception that integrated IR makes cameras mostly the same, according to new...