Completed
Intermediate Representations in Pytorch
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Client Side Deep Learning Optimization with PyTorch
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Who are we?
- 3 Why PyTorch?
- 4 Advantages of Eager Execution
- 5 Optimization necessitates looking under the hood
- 6 Axes of Optimization
- 7 Production Considerations
- 8 Scripting Handes control flow and other arbitrary
- 9 Scripting + Tracing
- 10 Intermediate Representations in Pytorch
- 11 Running in C++
- 12 Speed tips
- 13 Running Arbitrary Models
- 14 Lite Interpreter
- 15 What is Quantization?
- 16 Quantization in PyTorch
- 17 Eager Mode Quantization
- 18 Dynamk Quantization
- 19 Quantized Aware Training
- 20 Experimental Results
- 21 Channel Last Format
- 22 Addendum
