Best Practices for Real-time Intelligent Video Analytics

Best Practices for Real-time Intelligent Video Analytics

GOTO Conferences via YouTube Direct link

Intro

1 of 30

1 of 30

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Best Practices for Real-time Intelligent Video Analytics

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

  1. 1 Intro
  2. 2 Why intelligent video analytics?
  3. 3 Challenges with intelligent video analytics
  4. 4 Tips & tricks for efficient AI video analytics
  5. 5 Transfer learning
  6. 6 Data augmentation
  7. 7 Automatic mixed precision AMP
  8. 8 Quantization
  9. 9 Network pruning
  10. 10 Network graph optimizations
  11. 11 Kernel auto-tuning
  12. 12 Dynamic tensor memory upon inference
  13. 13 Multistream concurent execution
  14. 14 Free NVIDIA products designed to make your AI App efficient
  15. 15 NVIDIA's end-to-end AI workflow
  16. 16 TAO toolkit
  17. 17 high performance pre-trained vision AI models
  18. 18 Enabling beyond pre-trained AI models
  19. 19 Achieving state of the art accuracy for public datasets
  20. 20 NVIDIA TensorRT
  21. 21 TensorRT workflow
  22. 22 Triton inference server
  23. 23 DeepStream SDK
  24. 24 DeepStream application architecture
  25. 25 Pipelin efficiency with zero memory copies
  26. 26 NVIDIA graph composer
  27. 27 DeepStream video demo
  28. 28 Summary
  29. 29 Developer resources
  30. 30 Outro

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.