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

Anyvision Facial Recognition Tested on Aug 21, 2019
Anyvision is aiming for $1 billion in revenue by 2022, backed by $74 million in funding. But does their performance live up to the hype they have...
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...
Proactive CCTV "Only Affordable Video Archiving Solution" Profile on Aug 12, 2019
Proactive CCTV is claiming to offer "the only affordable video archiving solution on the market", reducing the storage typically required for H.265...
Dahua Analytics+ Tested on Aug 07, 2019
Dahua's analytics have performed poorly in past shootouts. But now, they claim their new Analytics+ "algorithms significantly improve accuracy and...
Honeywell Speaks On NDAA Ban, New Non-Banned Cameras and Cybersecurity on Aug 06, 2019
For years, Honeywell has depended on Dahua, a company with a poor cybersecurity track record and now banned by the US NDAA, for the development and...
Australia Security Full Show Report on Jul 25, 2019
IPVM went to Australia attending the 3 days of the Australia Security Exhibition: This was held at the ICC Sydney, as shown below: In this...
History of Video Surveillance on Jul 19, 2019
The video surveillance market has changed significantly since 2000, going from VCRs to ab emerging AI cloud era.  The goal of this history is to...
Wyze AI Analytics Tested - Beats Axis and Hikvision on Jul 17, 2019
$20 camera disruptor Wyze has released free person detection deep learning analytics to all of their users, claiming users will "Only get notified...
Ivideon Russian VSaaS Profile on Jun 27, 2019
Ivideon was an early VSaaS entrant, initially focusing on the consumer market, claiming massive growth to IPVM in 2014. We spoke to Ivideon, to...
Directory of 60 Video Surveillance Startups on Jun 25, 2019
This directory provides a list of video surveillance startups to help you see and research what companies are new or not yet broadly known. 2019...

Most Recent Industry Reports

TMA Apologizes to Amazon / Ring on Aug 23, 2019
Not only is Amazon / Ring making major incursions into the residential security market, the organization representing the biggest incumbents, The...
China Dahua Replaces Their Software With US Pepper on Aug 22, 2019
What does a US government banned company do to improve its security positioning in the US? Well, Dahua is unveiling a novel solution, partnering...
Security Integrators Outlook On Remaining Integrators In 2025 on Aug 22, 2019
The industry has changed substantially in the last decade, with the rise of IP cameras and the race to the bottom. Indeed, more changes may be...
First GDPR Facial Recognition Fine For Sweden School on Aug 22, 2019
A school in Sweden has been fined $20,000 for using facial recognition to keep attendance in what is Sweden's first GDPR fine. Notably, the fine is...
Anyvision Facial Recognition Tested on Aug 21, 2019
Anyvision is aiming for $1 billion in revenue by 2022, backed by $74 million in funding. But does their performance live up to the hype they have...
JCI Sues Wyze on Aug 21, 2019
The mega manufacturer / integrator JCI has sued the fast-growing $20 camera Seattle startup Wyze. Inside this note: Share the court...
Dahua 4K Camera Shootout on Aug 20, 2019
Dahua's new Pro Series 4K N85CL5Z claims to "deliver superior images in all lighting and environmental conditions", but how does this compare to...
ZK Teco Atlas Access Control Tested on Aug 20, 2019
Who needs access specialists? China-based ZKTeco claims its newest access panel 'makes it very easy for anyone to learn and install access control...
Uniview Beats Intel In Trademark Lawsuit on Aug 19, 2019
Uniview has won a long-running trademark lawsuit brought by Intel, with Beijing's highest court reversing an earlier Intel win, centered on...
Suprema Biometric Mass Leak Examined on Aug 19, 2019
While Suprema is rarely discussed even within the physical security market, the South Korean biometrics manufacturer made global news this past...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact