This course covers the learning outcomes and goals of TensorFlow model optimization through quantization and pruning. Students will learn about optimization, quantization, benchmarking, reducing precision, memory, and bandwidth pressure, as well as different quantization types and tools like TensorFlow flowlight converter. The teaching method includes lectures and discussions by TensorFlow performance experts. This course is intended for individuals interested in enhancing TensorFlow model efficiency and performance.
Overview
Syllabus
Introduction
Why is this important
Benefits of optimization
Resource constrained environment
Application constrained environment
Machine learning opportunities
Machine learning efficiency
Matrix multiply
Goals for optimization
Reducing precision
Reducing memory
Reducing bandwidth pressure
Reduce precision
Linear mapping
The problem
The implications
Quantization is complicated
Its hard to interpret
The model is not enough
Quantization types
Quantization benefits
Quantization tools
Posttraining
TensorFlow flowlight converter
Quantisation types
Highbury quantization
Accuracy
Interior Quantization
Results
Quantization training
Quantization model
Hybrid quantization
Integer quantization
Training scrape
Summary
Neural connection pruning
Stencil pruning
Tensor pruning
TensorFlow pruning API
Pruning schedule
Benefits of pruning
Roadmap
Better target hardware
Feedback
Tools
Questions
Training with integer constellations
Question
Taught by
TensorFlow
