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