Overview
This course on quantization aware training using TensorFlow covers the fundamentals of quantization aware training, the TensorFlow/Keras API for implementation, and techniques to recover lost accuracy. Students will learn how to quantize entire models, subsets of models, and even create custom quantization layers. The teaching method includes a tutorial format with practical examples and demonstrations. This course is intended for individuals interested in optimizing machine learning models using quantization techniques.
Syllabus
1 TensorFlow
The plan for the next hour
Optimizing ML Models
Model Optimization Toolkit
Uniform/Linear Quantization
Quantization is lossy
Quantization Aware Training (QAT)
How to recover lost accuracy?
Accuracy recovered using QAT
QAT and Keras
Quantize entire model
Quantize subset of model
Custom Quantize a layer
Quantize your own layer
Write your own algorithm (Quantizer)
QAT Keras APIs
Core Keras Abstractions
Keras Layer Lifecycle
Keras Model - Layer interaction
Keras Wrapper
Sample Wrapper
MOT Wrappers
Keras Model Transformer
Taught by
TensorFlow