Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.

AI Services and Serverless Workshop

This workshop will walk you trough building a serverless website, powered by AWS AI services, as part of the website backend.We will deploy a website on S3, use API Gateway and Lambda as our backend and integrate Amazon Rekognition to enrich user generated content.

  • Loggen Sie sich ein, um Kommentare anzuzeigen.

  • Gehören Sie zu den Ersten, denen das gefällt!

AI Services and Serverless Workshop

  1. 1. © 2019, Amazon Web Services, Inc. or its Affiliates. AI Services and Serverless Workshop Boaz Ziniman, Technical Evangelist Amazon Web Services @ziniman ziniman SSID: Guest Password: Unfabric@@2020
  2. 2. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman • Overview of Serverless computing and AI Services • Introduction to AWS services used in the workshop • Outline of the workshop scenario • Preview of the labs What to expect from this session
  3. 3. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Serverless Computing
  4. 4. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman In the beginning…
  5. 5. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman • Procurement • Power • Cooling • Asset tracking • Remote hands • IP transit • Colocation • Capacity planning • Hardware refreshes • Storage • Depreciation • Physical security • Networking equipment • Cabling Physical hardware – concern space
  6. 6. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman • Allows developers to obtain compute capacity on-demand • Create virtual servers in the cloud with the click of a button • Launched in 2006 Amazon Elastic Compute Cloud (EC2)
  7. 7. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Amazon Elastic Compute Cloud (EC2) Elasticity Provision Servers in Minutes Infrastructure as Code Programmatic Networking Global Footprint Match Capacity and Demand
  8. 8. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman • Configuration management • Security patches • Server utilization • Operating systems • Auto-scaling policies • Monitoring • Intrusion detection • Resiliency • Machine images • Access management • Capacity planning • Hourly billing • Code deployment Servers – concern space
  9. 9. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Serverless computing Fully managed • No provisioning • No system administration • No security patches • Fault tolerant Developer productivity • Focus on your application • Experiment and innovate quickly Continuous scaling • Scale up and down with demand • Never pay for idle resources Build and run applications and services without thinking of servers
  10. 10. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Step Functions
  11. 11. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Application Lifecycle in AWS Step Functions Visualize in the Console Define in JSON Monitor Executions
  12. 12. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Step Functions Tasks – Service Integrations AWS Lambda invoke a Lambda function AWS Batch submit a Batch job and wait for it to complete Amazon DynamoDB get, put, update or delete an item Amazon ECS/Fargate run an ECS task and waits for it to complete Amazon SNS publish a message to a SNS topic Amazon SQS send a SQS message AWS Glue start a Glue job Amazon SageMaker create a training or transform job
  13. 13. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman AI Services
  14. 14. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Our mission at AWS Put machine learning in the hands of every developer
  15. 15. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman M L F R A M E W O R K S & I N F R A S T R U C T U R E A I S E R V I C E S R E K O G N I T I O N I M A G E P O L L Y T R A N S C R I B E T R A N S L A T E C O M P R E H E N D & C O M P R E H E N D M E D I C A L L E XR E K O G N I T I O N V I D E O Vision Speech Chatbots A M A Z O N S A G E M A K E R B U I L D T R A I N F O R E C A S TT E X T R A C T P E R S O N A L I Z E D E P L O Y Pre-built algorithms & notebooks Data labeling (G R O U N D T R U T H ) One-click model training & tuning Optimization (N E O ) One-click deployment & hosting M L S E R V I C E S F r a m e w o r k s I n t e r f a c e s I n f r a s t r u c t u r e E C 2 P 3 & P 3 d n E C 2 C 5 F P G A s G R E E N G R A S S E L A S T I C I N F E R E N C E Reinforcement learningAlgorithms & models ( A W S M A R K E T P L A C E F O R M A C H I N E L E A R N I N G ) Language Forecasting Recommendations The Amazon ML stack: Broadest & deepest set of capabilities
  16. 16. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman A I S E R V I C E S R E K O G N I T I O N I M A G E P O L L Y T R A N S C R I B E T R A N S L A T E C O M P R E H E N D & C O M P R E H E N D M E D I C A L L E XR E K O G N I T I O N V I D E O Vision Speech Chatbots F O R E C A S TT E X T R A C T P E R S O N A L I Z E Language Forecasting Recommendations Put AI to work for your business
  17. 17. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Amazon Rekognition Easily add intelligent image and video analysis to your applications.
  18. 18. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Amazon Rekognition: Deep Learning-Based Image and Video Analysis
  19. 19. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Amazon Rekognition Benefits Low cost Your data is your ownServerless Rapid integration State of the art capabilities Continuous improvement
  20. 20. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Amazon Rekognition Image Object and scene detection Facial analysis Face recognition Text in image Unsafe image detection Celebrity recognition Face comparison
  21. 21. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Object & Scene Detection
  22. 22. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Smiling? Facial Analysis
  23. 23. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Crowd Detection – up to 100 faces
  24. 24. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Facial Search
  25. 25. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Explicit Nudity Nudity Graphic Male Nudity Graphic Female Nudity Sexual Activity Partial Nudity Suggestive Female Swimwear or Underwear Male Swimwear or Underwear Revealing Clothes Image Moderation
  26. 26. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Celebrity Recognition
  27. 27. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Text in Image
  28. 28. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman boazz: ~/ aws rekognition detect-labels --image '{"S3Object":{"Bucket":"demos.ziniman.com","Name":"photos/reko.jpg"}}’ { "Labels": [ { "Confidence": 99.14048767089844, "Name": "Human" }, { "Confidence": 99.1404800415039, "Name": "People" }, { "Confidence": 99.14048767089844, "Name": "Person" }…… Rekognition API Example
  29. 29. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman boazz: ~/ aws rekognition detect-faces --image '{"S3Object":{"Bucket":"demos.ziniman.com","Name":"photos/reko.jpg"}}' --attributes "ALL” { "FaceDetails": [ { .... "Gender": { "Confidence": 99.9211654663086, "Value": "Male" }, "AgeRange": { "High": 52, "Low": 35 }, .... Rekognition API Example
  30. 30. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Rekognition Lambda Python Example
  31. 31. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman The Workshop Image Recognition and Processing Backend
  32. 32. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman What we are going to build?
  33. 33. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman What we are going to build? AWS LambdaAmazon DynamoDB Amazon S3 AWS Step Functions Amazon Rekognition AWS Lambda Start state machine execution AWS Lambda AWS Lambda AWS Lambda Extract and validate image metadata from S3 object (EXIF, size, format, etc.) Generate image thumbnail Invoke Rekognition API Store data in DynamoDB
  34. 34. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman Step by Step
  35. 35. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman • Go to: https://bit.ly/ServerlessAI • User accounts • Your own account • Be careful with production/your company/shared/etc. accounts • Make sure all services are available in the region you are running in • WiFi • We are here to help • Cleanup Let the Fun Begin!
  36. 36. © 2019, Amazon Web Services, Inc. or its Affiliates. Thank You! Boaz Ziniman, Technical Evangelist Amazon Web Services @ziniman ziniman
  37. 37. © 2019, Amazon Web Services, Inc. or its Affiliates. @ziniman https://bit.ly/ServerlessAI SSID: Guest Password: Unfabric@@2020

×