This course provides an inside look into the TensorFlow team's internal training sessions on the TensorFlow Model Optimization Toolkit, focusing on quantization and pruning. The learning outcomes include understanding quantization and pruning techniques, exploring quantization tools, and implementing pruning examples. The course teaches skills such as quantization during and after training, quantization kernels, integer quantization, and pruning tools. The teaching method involves technical deep dives by the TensorFlow team. The intended audience for this course is individuals interested in optimizing TensorFlow models through quantization and pruning techniques.
Overview
Syllabus
Introduction
Overview
Why does this matter
Quantization is hard
Quantization during training
Quantization after training
Pruning
Quantization kernels
Quantitation spec
Cemetry
Perchannel condensation
Quantization tools
Integer Quantization
Hybrid Quantization
Postreading Integer Quantization
Quantization Accuracy
Quantization Benefits
Summary
Pruning Tools
Quantization API
Pruning Example
Pruning Summary
Matrix Multiplication
Taught by
TensorFlow
