Accelerating Vision AI Applications Using NVIDIA Transfer Learning Toolkit and Pre-Trained Models

Accelerating Vision AI Applications Using NVIDIA Transfer Learning Toolkit and Pre-Trained Models

NVIDIA Developer via YouTube Direct link

Intro

1 of 25

1 of 25

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Accelerating Vision AI Applications Using NVIDIA Transfer Learning Toolkit and Pre-Trained Models

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

  1. 1 Intro
  2. 2 TRAINING CHALLENGES
  3. 3 TRANSFER LEARNING TOOLKIT (TLT)
  4. 4 TRANSFER LEARNING TOOLKIT 2.0
  5. 5 PURPOSE BUILT PRE-TRAINED NETWORKS Highly Accurate Re-Trainable Out of Box Deployment
  6. 6 QUANTIZATION AWARE TRAINING Maintain comparable Performance & Sperdup Inference using INTB Precision
  7. 7 AUTOMATIC MIXED PRECISION (AMP) Train with half-precision while maintaining network accuracy same as single precision
  8. 8 INSTANCE SEGMENTATION - MASK R-CNN
  9. 9 PEOPLENET
  10. 10 FACE MASK DETECTION
  11. 11 TRAINING WORKFLOW
  12. 12 CONVERT TO KITTI
  13. 13 TLT SPEC FILES
  14. 14 PREPARE THE DATASET
  15. 15 TRAIN - PRUNE - EVALUATE
  16. 16 TRAINING SPEC - DATASET AND MODEL
  17. 17 EVALUATION SPEC
  18. 18 TRAINING & EVALUATION
  19. 19 MODEL PRUNING
  20. 20 RE-TRAIN & EVALUATE
  21. 21 TRAINING KPI
  22. 22 QUANTIZATION & EXPORT
  23. 23 INFERENCE SPEC
  24. 24 DEPLOY USING DEEPSTREAM
  25. 25 SUMMARY

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.