Upgrade to Pro — share decks privately, control downloads, hide ads and more …

MLKit-munich.pdf

Sponsored · Your Podcast. Everywhere. Effortlessly. Share. Educate. Inspire. Entertain. You do you. We'll handle the rest. →
Avatar for Sergii Khomenko Sergii Khomenko
September 08, 2018
48
0

 MLKit-munich.pdf

Avatar for Sergii Khomenko

Sergii Khomenko

September 08, 2018

More Decks by Sergii Khomenko

See All by Sergii Khomenko
Handle your Lambdas - From event-based processing to Continuous Integration / Munich AWS User Group - Mar 17, 2016
Avatar for Sergii Khomenko lc0
1
260
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - Mar 12, 2016
Avatar for Sergii Khomenko lc0
1
210
Building Data applications with Go: from Bloom filters to Data pipelines / FOSDEM - Jan 31, 2016
Avatar for Sergii Khomenko lc0
1
210
Building data pipelines: from simple to more advanced - hands-on experience / CrunchConf - Oct 29, 2015
Avatar for Sergii Khomenko lc0
0
100
Scaling up Business Intelligence from the scratch and to 15 countries worldwide / Budapest BI Forum - Oct 15, 2015
Avatar for Sergii Khomenko lc0
0
62
Secure Data Scalability at Stylight with Tableau Online and Amazon Redshift / Tableau Conference on Tour - Berlin - Jun 9, 2015
Avatar for Sergii Khomenko lc0
0
150
Helping Data Teams with Puppet / Puppet Camp London - Apr 13, 2015
Avatar for Sergii Khomenko lc0
0
250
Scaling your Tableau - Migrating from Tableau Online to a proper DWH solution / Munich Tableau User Group - Feb 26, 2015
Avatar for Sergii Khomenko lc0
0
70
Building Ranking Infrastructure: Data-Driven, Lean, Flexible - Sergii Khomenko, STYLIGHT / ApacheCon EU, Budapest 2014
Avatar for Sergii Khomenko lc0
0
65

Featured

See All Featured
Introduction to Domain-Driven Design and Collaborative software design
Avatar for Kenny Baas-Schwegler baasie
1
830
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
Avatar for panda_program panda_program
122
22k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
Avatar for Chris Coyier chriscoyier
508
140k
Build The Right Thing And Hit Your Dates
Avatar for Maggie C. maggiecrowley
39
3.2k
The Success of Rails: Ensuring Growth for the Next 100 Years
Avatar for Eileen M. Uchitelle eileencodes
47
8.2k
My Coaching Mixtape
Avatar for mlcsv mlcsv
0
140
Stewardship and Sustainability of Urban and Community Forests
Avatar for Eric Wiseman pwiseman
0
220
The agentic SEO stack - context over prompts
Avatar for schlessera schlessera
0
800
Learning to Love Humans: Emotional Interface Design
Avatar for Aarron Walter aarron
275
41k
Designing for Timeless Needs
Avatar for Cassini Nazir cassininazir
1
250
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
Avatar for Kenny Baas-Schwegler baasie
0
580
Digital Projects Gone Horribly Wrong (And the UX Pros Who Still Save the Day) - Dean Schuster
Avatar for UX Y'all uxyall
0
1.7k

Transcript

  1. Making your apps smart with MLKit From recognizing text to

    recognizing landmarks and all the way to deploying custom Tensorflow Lite Models Sergii Khomenko, @lc0d3r
  2. None
  3. None
  4. None
  5. None
  6. None
  7. None
  8. None
  9. None
  10. None
  11. None
  12. None
  13. None

  14. Dependencies

  15. On-device text recognition

  16. On-device text recognition

  17. On-device text recognition

  18. Cloud text recognition

  19. Cloud text recognition

  20. None
  21. None
  22. None
  23. None

  24. Key capabilities • TensorFlow Lite model hosting • On-device ML

    inference • Automatic model fallback • Automatic model updates
  25. None
  26. None
  27. None
  28. None
  29. None
  30. None
  31. None
  32. None
  33. None
  34. None
  35. None
  36. None
  37. None
  38. None
  39. None
  40. None
  41. None
  42. None
  43. None

  44. MLKit + Firebase • Easy model delivery • Let you

    focus on ML, not on mobile dev • “magic” features for free from Google
  45. None

  46. Links • https://codelabs.developers.google.com/codelabs/mlkit- android/index.html?index=..%2F..%2Fio2018#3 • https://firebase.google.com/docs/ml-kit/use-custom- models?authuser=0 • https://arxiv.org/abs/1503.02531