SlideShare a Scribd company logo
1 of 26
AIY VISION KIT
EMBEDDED ML FOR STEM AND MAKERS
Chad Hart
cwh.consulting
Product Consultant
cwh.consulting
chad@cwh.consulting
A blog for WebRTC developers
webrtcHacks.com
@webrtcHacks
WebRTC events & videos
www.krankygeek.com
@webrtclive
AboutMe
cwh.consulting
@chadwallacehart
chad@chadwallacehart.com
WhatistheAIY
VisionKit?
5/1/2018
cwh.consulting
A tiny box that let’s you do “AI Yourself” from Google.
This kit is focused on Computer Vision based on Tensorflow.
No internet connection is required.
WhatistheAIY
VisionKit?
5/1/2018
cwh.consulting
You need to assemble the kit yourself.
It takes 30 to 60 minutes.
JoyDetection
Demo
5/1/2018
cwh.consulting
The joy detection demo loads by default.
It does face detection and estimates your “Joy” score if you are smiling or frowning.
The default demo will illuminate the LED button according to the average score it sees
across all faces.
How doyouget
one?
5/1/2018
cwh.consulting
The new, 1.1 version is available for sale at Target stores.
The Kit
AIY Voice Kit
What’sinthe
box?
5/1/2018
cwh.consulting
The new, 1.1 contains everything needed for operation except a USB power supply.
RaspberryPiZeroWH
5/1/2018
cwh.consulting
It runs on a tiny Raspberry Pi Zero.
GPIO headers are required and WiFi is handy, so the kit ships with the WH version of the Pi Zero.
PiCamera
5/1/2018
cwh.consulting
And it includes the latest Pi Camera.
VisionBonnet
5/1/2018
cwh.consulting
All of the kit’s magic is performed on the Vision Bonnet – an add on board.
IntelMovidius
MA2450
Vision Processing Unit
5/1/2018
cwh.consulting
The most important piece of hardware is the intel Movidius VPU chip.
This is a specialized chip designed for running machine learning graphs at low power.
You can also buy this check as part of a USB dongle from Intel (Intel NCS) for use with Intel’s SDK.
The AIY Kit team built their own SDK and optimized it to work with Tensorflow.
Othergoodies
wewon’ttalk
abouttoday
 Button with multi-color
LED
 Privacy LED
 Buzzer
 Micro controller chip on
Bonnet with extra GPIO
pins, LEDs, and button
5/1/2018
cwh.consulting
The kit comes with lots of other interfaces and hardware options
Development
AIY Voice Kit
Models
Face / Joy
detector
Bounding box
Joy score
Dog / Cat /
Human
Detector
Object class
Confidence
score
Bounding box
Dish Classifier
Food object
Confidence
score
Image Classifier
/ Google Image
Classifier
Image
classifier (1000
classes?)
Confidence
score
Nature
Explorer
Image
classification of
4,080 different
species
5/1/2018
cwh.consultingGoogle maintains several computer vision (CV) models that can be loaded on to the kit.
Several of these were recently added and hopefully more will come soon.
Process
1. Develop the
model
2. Train 3. Freeze graph &
compile
4. Deploy
5/1/2018
cwh.consultingModels need to be trained outside of the kit.
Then they can be compiled for the AIY Vision Kit and deployed there.
Custommodels
 Tensorflow Model Compiler
 Only works on x86 64 Ubuntu
 Lots of limitations on the model – specific operators and
configuration require
Build your own
Retrain an existing model
5/1/2018
cwh.consulting
./bonnet_model_compiler.par 
--
frozen_graph_path=cat_detector_interference_graph_aiy/frozen_inference_graph.p
b 
--output_graph_path=cat_detector.binaryproto 
--input_tensor_name="input" 
--output_tensor_names="concat,concat_1" 
--input_tensor_size=160 
--debug
There are caveats compiling to the AIY Vision Kit.
I have not been able to get this to work (or seen someone else do this), but I think we are very close – see
https://github.com/google/aiyprojects-raspbian/issues/314
Demos
AIY Vision Kit
5/1/2018
cwh.consulting
Cat detection using the built in cat/dog/human detector: https://youtu.be/NguWj9K1MJs
Face detection: https://webrtchacks.com/wp-content/uploads/2018/02/face_detection_camera.py-preview.mp4?_=1
What does it all mean?
2 things…
5/1/2018
cwh.consulting
5/1/2018
cwh.consulting
Cloud
Edge
1. Applying Machine Learning at the edge – not just the cloud
Cloudvs.Edge
Privacy
Latency
Power
Costs
considerations
5/1/2018
cwh.consultingThere are several reasons why you might not want to push your machine learning to the cloud
EdgeML
Examples of Computer Vision on
the Movidius
5/1/2018
cwh.consulting
Here are some real products that use the Movidius chip for running machine learning on-device
STEM
5/1/2018
cwh.consulting
STEM
5/1/2018
cwh.consulting
2. The kit is designed to expose high-schoolers to using AI technologies, not for PhD’s
Google is trying to make ML tangible for a large audience.
AIYLinks
 https://aiyprojects.withgoogle.com/vision
 https://github.com/google/aiyprojects-raspbian
 https://webrtchacks.com/aiy-vision-kit-uv4l-web-server/
5/1/2018
cwh.consulting
Contact
chadwhart@gmail.com
@chadwallacehart
cwh.consulting
webrtcHacks.com
github.com/chadwallacehart
5/1/2018
cwh.consulting

More Related Content

Similar to AIY Vision Kit - Embedded ML for STEM and Makers (GDG Boston Tensorflow)

Machine Learning Model for Gender Detection
Machine Learning Model for Gender DetectionMachine Learning Model for Gender Detection
Machine Learning Model for Gender Detection
TecnoIncentive
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminology
ClintParis
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminology
ClintParis
 
WBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docx
WBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docxWBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docx
WBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docx
jessiehampson
 

Similar to AIY Vision Kit - Embedded ML for STEM and Makers (GDG Boston Tensorflow) (20)

Building a Beer Recommender with Yhat (PAPIs.io - November 2014)
Building a Beer Recommender with Yhat (PAPIs.io - November 2014)Building a Beer Recommender with Yhat (PAPIs.io - November 2014)
Building a Beer Recommender with Yhat (PAPIs.io - November 2014)
 
產品設計的0到1,與1到1億
產品設計的0到1,與1到1億產品設計的0到1,與1到1億
產品設計的0到1,與1到1億
 
AI-Volution: WordPress Developer’s Guide to Evolve in the Age of AI by Abhish...
AI-Volution: WordPress Developer’s Guide to Evolve in the Age of AI by Abhish...AI-Volution: WordPress Developer’s Guide to Evolve in the Age of AI by Abhish...
AI-Volution: WordPress Developer’s Guide to Evolve in the Age of AI by Abhish...
 
[DevDay2019] Hands-on Machine Learning on Google Cloud Platform - By Thanh Le...
[DevDay2019] Hands-on Machine Learning on Google Cloud Platform - By Thanh Le...[DevDay2019] Hands-on Machine Learning on Google Cloud Platform - By Thanh Le...
[DevDay2019] Hands-on Machine Learning on Google Cloud Platform - By Thanh Le...
 
Eye Tracking Automated Coding
Eye Tracking Automated CodingEye Tracking Automated Coding
Eye Tracking Automated Coding
 
2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net2020 04 04 NetCoreConf - Machine Learning.Net
2020 04 04 NetCoreConf - Machine Learning.Net
 
Enabling Lean at Enterprise Scale: Lean Engineering in Action
Enabling Lean at Enterprise Scale: Lean Engineering in ActionEnabling Lean at Enterprise Scale: Lean Engineering in Action
Enabling Lean at Enterprise Scale: Lean Engineering in Action
 
Html5- what you need to know and why you should care
Html5- what you need to know and why you should careHtml5- what you need to know and why you should care
Html5- what you need to know and why you should care
 
Continuous Validation - Lean Startup Machine Sydney 2013
Continuous Validation - Lean Startup Machine Sydney 2013Continuous Validation - Lean Startup Machine Sydney 2013
Continuous Validation - Lean Startup Machine Sydney 2013
 
How to test an AI application
How to test an AI applicationHow to test an AI application
How to test an AI application
 
Using Clojure, NoSQL Databases and Functional-Style JavaScript to Write Gext-...
Using Clojure, NoSQL Databases and Functional-Style JavaScript to Write Gext-...Using Clojure, NoSQL Databases and Functional-Style JavaScript to Write Gext-...
Using Clojure, NoSQL Databases and Functional-Style JavaScript to Write Gext-...
 
Building Better IoT Applications without Servers
Building Better IoT Applications without ServersBuilding Better IoT Applications without Servers
Building Better IoT Applications without Servers
 
Easy path to machine learning
Easy path to machine learningEasy path to machine learning
Easy path to machine learning
 
Machine Learning Model for Gender Detection
Machine Learning Model for Gender DetectionMachine Learning Model for Gender Detection
Machine Learning Model for Gender Detection
 
Technology Based Testing
Technology Based TestingTechnology Based Testing
Technology Based Testing
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminology
 
Comment tirer partie de Visual Studio Online pour vos développements SharePoint
Comment tirer partie de Visual Studio Online pour vos développements SharePointComment tirer partie de Visual Studio Online pour vos développements SharePoint
Comment tirer partie de Visual Studio Online pour vos développements SharePoint
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminology
 
WBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docx
WBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docxWBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docx
WBSCode Wedding Task Project mangerProgram ownerBridgroomFinance .docx
 
Pink by Bon
Pink by BonPink by Bon
Pink by Bon
 

More from Chad Hart

More from Chad Hart (14)

Kill Your IVR with a Voicebot (ClueCon 2019)
Kill Your IVR with a Voicebot (ClueCon 2019)Kill Your IVR with a Voicebot (ClueCon 2019)
Kill Your IVR with a Voicebot (ClueCon 2019)
 
WebRTC Check-in (from WebRTC Boston 6)
WebRTC Check-in (from WebRTC Boston 6)WebRTC Check-in (from WebRTC Boston 6)
WebRTC Check-in (from WebRTC Boston 6)
 
AI in RTC - RTC Korea 2018
AI in RTC - RTC Korea 2018AI in RTC - RTC Korea 2018
AI in RTC - RTC Korea 2018
 
Boosting business with WebRTC - ClueCon 2017
Boosting business with WebRTC - ClueCon 2017Boosting business with WebRTC - ClueCon 2017
Boosting business with WebRTC - ClueCon 2017
 
Kamailio World 2017: Getting Real with WebRTC
Kamailio World 2017: Getting Real with WebRTCKamailio World 2017: Getting Real with WebRTC
Kamailio World 2017: Getting Real with WebRTC
 
6 Months of WebRTC in 10 minutes
6 Months of WebRTC in 10 minutes6 Months of WebRTC in 10 minutes
6 Months of WebRTC in 10 minutes
 
Astricon WebRTC Update
Astricon WebRTC UpdateAstricon WebRTC Update
Astricon WebRTC Update
 
WebRTC From Asterisk to Headline - MoNage
WebRTC From Asterisk to Headline - MoNageWebRTC From Asterisk to Headline - MoNage
WebRTC From Asterisk to Headline - MoNage
 
ClueCon 2016: Should you use WebRTC?
ClueCon 2016: Should you use WebRTC?ClueCon 2016: Should you use WebRTC?
ClueCon 2016: Should you use WebRTC?
 
WebRTC Hacks: Lessons Learned
WebRTC Hacks: Lessons LearnedWebRTC Hacks: Lessons Learned
WebRTC Hacks: Lessons Learned
 
WebRTC for Billions
WebRTC for BillionsWebRTC for Billions
WebRTC for Billions
 
The Future of Real Time Communications
The Future of Real Time CommunicationsThe Future of Real Time Communications
The Future of Real Time Communications
 
What's Next for WebRTC
What's Next for WebRTCWhat's Next for WebRTC
What's Next for WebRTC
 
Getting Started with WebRTC
Getting Started with WebRTCGetting Started with WebRTC
Getting Started with WebRTC
 

Recently uploaded

CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 

Recently uploaded (20)

Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdf
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 

AIY Vision Kit - Embedded ML for STEM and Makers (GDG Boston Tensorflow)

Editor's Notes

  1. sudo systemctl stop joy_detection_demo.service sudo chown pi: /tmp/uv4l-raspidisp.socket
  2. sudo systemctl stop joy_detection_demo.service sudo chown pi: /tmp/uv4l-raspidisp.socket pi@100.71.52.57 https://www.youtube.com/watch?v=NguWj9K1MJs&list=PLZa3EnwUZVaLqYXFjl1jMNugsCBsbtc8x