Edge AI Design Strategy for C2C E-Commerce Applications

Edge AI Design Strategy for C2C E-Commerce Applications

Linux Foundation via YouTube Direct link

Background replacement on Google Meet

3 of 24

3 of 24

Background replacement on Google Meet

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Edge AI Design Strategy for C2C E-Commerce Applications

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Agenda
  3. 3 Background replacement on Google Meet
  4. 4 Client-side ML in Mercari
  5. 5 Why Client-side ML
  6. 6 How to develop Client-side ML
  7. 7 For more advanced use cases
  8. 8 Four key points concerning production
  9. 9 Is the Server-side enough?
  10. 10 In the case of Mercari Lens
  11. 11 Model architecture
  12. 12 Inference on Streaming Media
  13. 13 Pre/Post Process
  14. 14 Introduce MediaPipe
  15. 15 Define a process pipeline
  16. 16 Inference with the pipeline
  17. 17 Optimize the pipeline
  18. 18 Validation
  19. 19 Tools for web
  20. 20 Unfortunately, NO
  21. 21 Architecture for native application
  22. 22 We could migrate to web!
  23. 23 Native like performance on web
  24. 24 Conclusion

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.