SlideShare a Scribd company logo
1 of 18
Parking: Deeplearning to the rescue
The issue
What is DeepLens
Let’s be smart
• No custom algorithm
• All in a sagemaker notebook
• RESNET
Learning data: 600
images
Labeling data with
AWS Rekognition
• { "Name": "Car", "Confidence": 99.79415130615234,
"Instances": [ { "BoundingBox": { "Width":
0.17780812084674835, "Height": 0.29317113757133484,
"Left": 0.5473999977111816, "Top": 0.6403614282608032
}, "Confidence": 99.79415130615234 }, { "BoundingBox": {
"Width": 0.14768852293491364, "Height":
0.24963326752185822, "Left": 0.341799259185791, "Top":
0.6650670766830444 }, "Confidence": 99.78534698486328
}, { "BoundingBox": { "Width": 0.06380444765090942,
"Height": 0.09763874113559723, "Left":
0.36006444692611694, "Top": 0.44678395986557007 },
"Confidence": 98.7358627319336 }, { "BoundingBox": {
"Width": 0.05265254154801369, "Height":
0.09502611309289932, "Left": 0.44609522819519043,
"Top": 0.45088955760002136 }, "Confidence":
97.01277923583984 }, { "BoundingBox": { "Width":
0.058230262249708176, "Height": 0.11082297563552856,
"Left": 0.5307189226150513, "Top": 0.434757262468338 },
"Confidence": 94.97325897216797 }, { "BoundingBox": {
"Width": 0.04611233249306679, "Height":
0.035156410187482834, "Left": 0.630984902381897, "Top":
0.2887030839920044 }, "Confidence": 81.58234405517578 }
],
Make a
RecordIO file
Select valid files
Cleanup files (now I know)
Make a directoryfile
Use im2rec.py to create a huge
RecordIO file.
Kickoff sagemaker
Just opened up an image classification example
based upon Resnet.
And trained it with changing parameters, by
editing the notebook.
After 10 iterations (about 30 hours of training)
using 70% trainingdata the best score was 81%.
Which is not good enough……
What went
wrong.
SOME CARS….
DARK SURROUNDINGS
CARS IN THE BACKGROUND
RAIN
Did the thing
that I did not
want to do.
Slice the image
and infer all
separate images.
Kickoff sagemaker again
Just opened up an image classification example
based upon Resnet.
And trained it once for four hours
After 1 iteration using 70% trainingdata the score
would be 99% (for 1 spot)
This is satisfactory
Make the
lambda
function a bit
smarter.
Use CV to make 4
images out of the
camera image.
Resize these images
Infer every image
until one spot is
free.
Send the result to
an s3 bucket
Move model and Lambda to DeepLens
API-Gateway > AWS Lambda > SNS
What I
learned
• DeepLens is developer hardware
• Windows require cleaning
• Preprocessing is am must
• Expect connectionproblems when moving the
camera
• Writing logging is a good thing
• Put gaffertape on the blue leds
• Think twice before you promise your family
something
leon@devoto.nl
06-51613265
degeling@gmail.com

More Related Content

What's hot

Google Cloud Pricing Calculators
Google Cloud Pricing CalculatorsGoogle Cloud Pricing Calculators
Google Cloud Pricing CalculatorsDigital Shende
 
SharePoint meetup Speaking Deck - Knowing the formula
SharePoint meetup Speaking Deck -  Knowing the formulaSharePoint meetup Speaking Deck -  Knowing the formula
SharePoint meetup Speaking Deck - Knowing the formulaKenneth Cooper
 
Cloud Computing for newbie
Cloud Computing for newbieCloud Computing for newbie
Cloud Computing for newbieshoujs
 
Go Serverless - Golang NE February 2018
Go Serverless - Golang NE February 2018Go Serverless - Golang NE February 2018
Go Serverless - Golang NE February 2018Mark Hemmings
 
2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...
2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...
2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...GIS in the Rockies
 
Getting started with machine learning | Mike Fowler
Getting started with machine learning | Mike FowlerGetting started with machine learning | Mike Fowler
Getting started with machine learning | Mike FowlerAWSCOMSUM
 
Getting started with Machine Learning
Getting started with Machine LearningGetting started with Machine Learning
Getting started with Machine LearningMike Fowler
 
.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time
.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time
.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no timeNETFest
 
Day 3 - Maintaining Performance & Availability While Lowering Costs with AWS
Day 3 - Maintaining Performance & Availability While Lowering Costs with AWSDay 3 - Maintaining Performance & Availability While Lowering Costs with AWS
Day 3 - Maintaining Performance & Availability While Lowering Costs with AWSAmazon Web Services
 

What's hot (9)

Google Cloud Pricing Calculators
Google Cloud Pricing CalculatorsGoogle Cloud Pricing Calculators
Google Cloud Pricing Calculators
 
SharePoint meetup Speaking Deck - Knowing the formula
SharePoint meetup Speaking Deck -  Knowing the formulaSharePoint meetup Speaking Deck -  Knowing the formula
SharePoint meetup Speaking Deck - Knowing the formula
 
Cloud Computing for newbie
Cloud Computing for newbieCloud Computing for newbie
Cloud Computing for newbie
 
Go Serverless - Golang NE February 2018
Go Serverless - Golang NE February 2018Go Serverless - Golang NE February 2018
Go Serverless - Golang NE February 2018
 
2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...
2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...
2012 Vendor Track, How City and County of Denver Serves GIS Data, Genie Hays,...
 
Getting started with machine learning | Mike Fowler
Getting started with machine learning | Mike FowlerGetting started with machine learning | Mike Fowler
Getting started with machine learning | Mike Fowler
 
Getting started with Machine Learning
Getting started with Machine LearningGetting started with Machine Learning
Getting started with Machine Learning
 
.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time
.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time
.NET Fest 2018. Alex Pshul. Xamarin + Azure Maps = Waze in no time
 
Day 3 - Maintaining Performance & Availability While Lowering Costs with AWS
Day 3 - Maintaining Performance & Availability While Lowering Costs with AWSDay 3 - Maintaining Performance & Availability While Lowering Costs with AWS
Day 3 - Maintaining Performance & Availability While Lowering Costs with AWS
 

Similar to Parking: DeepLens to the rescue

Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...
Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...
Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...Amazon Web Services
 
Machine Learning for Web Developers
Machine Learning for Web DevelopersMachine Learning for Web Developers
Machine Learning for Web DevelopersRiza Fahmi
 
AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...
AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...
AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...Amazon Web Services
 
AWS Stockholm Meetup June 2019 - Cybercom DeepRacer story
AWS Stockholm Meetup June 2019 - Cybercom DeepRacer storyAWS Stockholm Meetup June 2019 - Cybercom DeepRacer story
AWS Stockholm Meetup June 2019 - Cybercom DeepRacer storyRolf Koski
 
AWS Finland Meetup June 2019 - DeepRacer story
AWS Finland Meetup June 2019 - DeepRacer storyAWS Finland Meetup June 2019 - DeepRacer story
AWS Finland Meetup June 2019 - DeepRacer storyJouni Luoma
 
AWS Summit Berlin 2017
AWS Summit Berlin 2017AWS Summit Berlin 2017
AWS Summit Berlin 2017Rino Montiel
 
Deep Learning in Production: Serving Image Models at Scale
Deep Learning in Production: Serving Image Models at ScaleDeep Learning in Production: Serving Image Models at Scale
Deep Learning in Production: Serving Image Models at ScaleAlexey Grigorev
 
AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...Apache MXNet
 
AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...Vandana Kannan
 
"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019
"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019
"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019Provectus
 
Scaling Machine Learning from zero to millions of users (May 2019)
Scaling Machine Learning from zero to millions of users (May 2019)Scaling Machine Learning from zero to millions of users (May 2019)
Scaling Machine Learning from zero to millions of users (May 2019)Julien SIMON
 
Building and scaling a B2D service, the bootstrap way
Building and scaling a B2D service, the bootstrap wayBuilding and scaling a B2D service, the bootstrap way
Building and scaling a B2D service, the bootstrap wayNadav Soferman
 
DataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT WorkshopDataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT WorkshopAmazon Web Services
 
Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Turi, Inc.
 
Machine Learning inference at the Edge
Machine Learning inference at the EdgeMachine Learning inference at the Edge
Machine Learning inference at the EdgeJulien SIMON
 
Getting Intimate with Images on Android with James Halpern
Getting Intimate with Images on Android with James HalpernGetting Intimate with Images on Android with James Halpern
Getting Intimate with Images on Android with James HalpernFITC
 
Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...
Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...
Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...gdgsurrey
 

Similar to Parking: DeepLens to the rescue (20)

Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...
Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...
Intro to Amazon Lightsail and Launching Your First Application on Amazon Ligh...
 
Machine Learning for Web Developers
Machine Learning for Web DevelopersMachine Learning for Web Developers
Machine Learning for Web Developers
 
AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...
AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...
AWS DeepLens Workshop: Building Computer Vision Applications - BDA201 - Atlan...
 
AWS Stockholm Meetup June 2019 - Cybercom DeepRacer story
AWS Stockholm Meetup June 2019 - Cybercom DeepRacer storyAWS Stockholm Meetup June 2019 - Cybercom DeepRacer story
AWS Stockholm Meetup June 2019 - Cybercom DeepRacer story
 
AWS Finland Meetup June 2019 - DeepRacer story
AWS Finland Meetup June 2019 - DeepRacer storyAWS Finland Meetup June 2019 - DeepRacer story
AWS Finland Meetup June 2019 - DeepRacer story
 
Dato Keynote
Dato KeynoteDato Keynote
Dato Keynote
 
AWS Summit Berlin 2017
AWS Summit Berlin 2017AWS Summit Berlin 2017
AWS Summit Berlin 2017
 
Deep Learning in Production: Serving Image Models at Scale
Deep Learning in Production: Serving Image Models at ScaleDeep Learning in Production: Serving Image Models at Scale
Deep Learning in Production: Serving Image Models at Scale
 
AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...
 
AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...AI powered emotion recognition: From Inception to Production - Global AI Conf...
AI powered emotion recognition: From Inception to Production - Global AI Conf...
 
"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019
"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019
"Scaling ML from 0 to millions of users", Julien Simon, AWS Dev Day Kyiv 2019
 
Scaling Machine Learning from zero to millions of users (May 2019)
Scaling Machine Learning from zero to millions of users (May 2019)Scaling Machine Learning from zero to millions of users (May 2019)
Scaling Machine Learning from zero to millions of users (May 2019)
 
Building and scaling a B2D service, the bootstrap way
Building and scaling a B2D service, the bootstrap wayBuilding and scaling a B2D service, the bootstrap way
Building and scaling a B2D service, the bootstrap way
 
DataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT WorkshopDataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT Workshop
 
Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015Strata London - Deep Learning 05-2015
Strata London - Deep Learning 05-2015
 
Machine Learning inference at the Edge
Machine Learning inference at the EdgeMachine Learning inference at the Edge
Machine Learning inference at the Edge
 
Scaling Deep Learning
Scaling Deep LearningScaling Deep Learning
Scaling Deep Learning
 
Mlcc #4
Mlcc #4Mlcc #4
Mlcc #4
 
Getting Intimate with Images on Android with James Halpern
Getting Intimate with Images on Android with James HalpernGetting Intimate with Images on Android with James Halpern
Getting Intimate with Images on Android with James Halpern
 
Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...
Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...
Certification Study Group - Professional ML Engineer Session 3 (Machine Learn...
 

Recently uploaded

AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 

Recently uploaded (20)

AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 

Parking: DeepLens to the rescue

  • 1.
  • 5. Let’s be smart • No custom algorithm • All in a sagemaker notebook • RESNET
  • 7. Labeling data with AWS Rekognition • { "Name": "Car", "Confidence": 99.79415130615234, "Instances": [ { "BoundingBox": { "Width": 0.17780812084674835, "Height": 0.29317113757133484, "Left": 0.5473999977111816, "Top": 0.6403614282608032 }, "Confidence": 99.79415130615234 }, { "BoundingBox": { "Width": 0.14768852293491364, "Height": 0.24963326752185822, "Left": 0.341799259185791, "Top": 0.6650670766830444 }, "Confidence": 99.78534698486328 }, { "BoundingBox": { "Width": 0.06380444765090942, "Height": 0.09763874113559723, "Left": 0.36006444692611694, "Top": 0.44678395986557007 }, "Confidence": 98.7358627319336 }, { "BoundingBox": { "Width": 0.05265254154801369, "Height": 0.09502611309289932, "Left": 0.44609522819519043, "Top": 0.45088955760002136 }, "Confidence": 97.01277923583984 }, { "BoundingBox": { "Width": 0.058230262249708176, "Height": 0.11082297563552856, "Left": 0.5307189226150513, "Top": 0.434757262468338 }, "Confidence": 94.97325897216797 }, { "BoundingBox": { "Width": 0.04611233249306679, "Height": 0.035156410187482834, "Left": 0.630984902381897, "Top": 0.2887030839920044 }, "Confidence": 81.58234405517578 } ],
  • 8. Make a RecordIO file Select valid files Cleanup files (now I know) Make a directoryfile Use im2rec.py to create a huge RecordIO file.
  • 9. Kickoff sagemaker Just opened up an image classification example based upon Resnet. And trained it with changing parameters, by editing the notebook. After 10 iterations (about 30 hours of training) using 70% trainingdata the best score was 81%. Which is not good enough……
  • 10. What went wrong. SOME CARS…. DARK SURROUNDINGS CARS IN THE BACKGROUND RAIN
  • 11. Did the thing that I did not want to do. Slice the image and infer all separate images.
  • 12. Kickoff sagemaker again Just opened up an image classification example based upon Resnet. And trained it once for four hours After 1 iteration using 70% trainingdata the score would be 99% (for 1 spot) This is satisfactory
  • 13. Make the lambda function a bit smarter. Use CV to make 4 images out of the camera image. Resize these images Infer every image until one spot is free. Send the result to an s3 bucket
  • 14. Move model and Lambda to DeepLens
  • 15.
  • 16. API-Gateway > AWS Lambda > SNS
  • 17. What I learned • DeepLens is developer hardware • Windows require cleaning • Preprocessing is am must • Expect connectionproblems when moving the camera • Writing logging is a good thing • Put gaffertape on the blue leds • Think twice before you promise your family something leon@devoto.nl

Editor's Notes

  1. At re:invent and similar conferences one tends to receive endless amounts of swag, not all swag is welcomed by my familymembers. The hoodies rank high on the not wanted list . But some of the electronic items are welcomed by curiosity.
  2. Upon explaining the possibilities of AWS-DeepLens my family had an idea
  3. “Can you notify me I if there is parking available next to our house, as soon as I drive into our village?’ Sure I said. I figured my total lack of knowledge of machinelearning would easily be overcome.
  4. Explain components in this diagram. Explain the lambdafuntion is running local, but stress the coonectivity of the device and the possibility to integrate remote AWS services.
  5. Finding empty parkingplaces based upon a cameraimage is probably cheaper and easier using a specific algorithm coded for this use-case. If you use cv and flatten some parts of the image, and look at variance in color, or look for certain features (curved lines are a great indicator) For this challenge we expect to train a model without adding any hand crafted ‘intelligence’ and let machinelearning figure out how to detected available parkingplaces. Explain the basic steps in the diagram.
  6. Learning data was produced by placing the camera in a window and make the lambda function send an image to s3 every 5 minutes for a week. We deleted identical images by comparing resized and flattened versions of concurrent images. (Had to take extra measures to remove the flag in the picture that made every daytime picture unique.
  7. Tagging the picture with a value of available or full was done by running a s3 batch operation which called aws rekognition. We parsed rekognitions results and checked for the presence of cars within certain coordinates after calculating parking availability we tagged the s3 files with the availability.
  8. Machinelearning apparently requires RecordIO files, so we created them. We should have done more cleanup and should have left out some delivery-trucks, and pictures where the window so moist that the picture was unusable. Making RecordIO file takes disk and time.
  9. I used the standard highlevel image classification sample notebook in Sagemaker and moved in my own images. After putting in 30 hours of training with changing parameter.
  10. Some (red) cars were only visible on full parking lots. The model recognized them as meaning: Parkinglot full. At night the parking is full, The model decided that dark sky means: Parkinglot full. The cars in the background seemed influential. During rain dark cars were not recognized.
  11. Since I did not get the model good enough I decided to make new training data by slicing all images, resizing to a standard size this became the new training-data. (Used 400 images per parking-spot)
  12. Run the same notebook.
  13. Just deployed through deeplens console.
  14. Since I did want to send a notification als soon as you enter the village I installed the IFTTT app on the phone. Made it call a webhook upon entering our village.
  15. The webhook activates an api-gateway that triggers a lambda function, that check the status on S3 and sends an SNS notification, that delivered a sms-message that I configured to a specific ringtone. By using two separate caller-id’s for Full and available I was able to have a different ringtone for both conditions. (Could not get my family to pose in this picture, so this is a photo from google)
  16. DeepLens can get hot and does chrash about once a week.