This tutorial explains the basics behind different quantization approaches explaining the math and the intuitions. Explains how the mapping is done from float32 precision to int8 precision.
Link to the Slides : drive.google.c...
----------------------------------------------------------------------------------------------------------------
Reference materials for further reading.
A White Paper on Neural Network Quantization - arxiv.org/abs/...
Introduction to Quantization on PyTorch - pytorch.org/bl...
Nvidia docs on Quantisation Basics - docs.nvidia.co...
----------------------------------------------------------------------------------------------------------------
BGM Credits
🔻
Song: "Sappheiros - Falling (Ft. eSoreni) [Chill]" is under a Creative Commons license (CC-BY)
Music promoted by BreakingCopyright: bit.ly/Sappheir...
🔺
Негізгі бет Quantization in Neural Networks - Basics Explained | Affine and Symmetric Quantization
Пікірлер: 10