Quantization

Scalar Quantization, Uniform Quantization, Linear Quantization, Non uniform Quantization   스칼라 양자화, 균일 양자화, 균등 양자화, 선형 양자화

http://www.ktword.co.kr/test/view/view.php?m_temp1=4399

 

 

Quantization for Neural Networks

https://leimao.github.io/article/Neural-Networks-Quantization/#Introduction

 

 

[Lightweight DL] Quantization (1/3)
https://jin-choi.tistory.com/18#intro

 

[Lightweight DL] Quantization (2/3)
https://jin-choi.tistory.com/19

 

[Lightweight DL] Quantization (3/3)
https://jin-choi.tistory.com/29

 

딥러닝의 Quantization (양자화)와 Quantization Aware Training

https://gaussian37.github.io/dl-concept-quantization/

 

 

[Quantization] Integer Quantization for Deep Learning Inference
https://computistics.tistory.com/30

 

[Quantization] Low-Bit 양자화 적용 이슈
https://computistics.tistory.com/29

 

Intuitive Explanation of Straight-Through Estimators with PyTorch Implementation
https://hassanaskary.medium.com/intuitive-explanation-of-straight-through-estimators-with-pytorch-implementation-71d99d25d9d0

 

The concept of straight through estimator (STE) [closed]
https://stackoverflow.com/questions/38361314/the-concept-of-straight-through-estimator-ste

 

 

Int 8 Quantization - Google's solution
https://jin-choi.tistory.com/18#int8-google

 

Int 8 Quantization - Nvidia's solution
https://jin-choi.tistory.com/18#int8-nvidia

 

Sub-8bit quantization - 1) Log Quantization
https://jin-choi.tistory.com/19#logquant

 

Sub-8bit quantization - 2) Weighted Quantization
https://jin-choi.tistory.com/19#weightquant

 

Sub-8bit quantization - 3) Outlier Quantization
https://jin-choi.tistory.com/19#outlierquant

 

4bit quantization - 1) Precision Highway
https://jin-choi.tistory.com/19#precisionhighway

 

4bit quantization - 2) Learnable Quantization
https://jin-choi.tistory.com/19#learnablequant

 

Sub-4bit quantization - PROFIT with MobileNet v3 case
https://jin-choi.tistory.com/19#profit

 

Binary quantization

 

 

딥러닝 모델 압축 방법론과 BERT 압축
https://blog.est.ai/2020/03/%EB%94%A5%EB%9F%AC%EB%8B%9D-%EB%AA%A8%EB%8D%B8-%EC%95%95%EC%B6%95-%EB%B0%A9%EB%B2%95%EB%A1%A0%EA%B3%BC-bert-%EC%95%95%EC%B6%95/

 

How We Scaled Bert To Serve 1+ Billion Daily Requests on CPUs
https://medium.com/@quocnle/how-we-scaled-bert-to-serve-1-billion-daily-requests-on-cpus-d99be090db26

 

Benefits of Fixed-Point Hardware
https://www.mathworks.com/help/fixedpoint/gs/benefits-of-fixed-point-hardware.html

 

Introduction to Deep Learning : Downsizing Neural Networks by Quantization
https://www.youtube.com/watch?v=DDelqfkYCuo&ab_channel=NeuralNetworkConsole 

 

딥러닝 Quantization(양자화) 정리
https://velog.io/@jooh95/%EB%94%A5%EB%9F%AC%EB%8B%9D-Quantization%EC%96%91%EC%9E%90%ED%99%94-%EC%A0%95%EB%A6%AC

 

Introduction to Quantization on PyTorch
https://pytorch.org/blog/introduction-to-quantization-on-pytorch/

 

(BETA) DYNAMIC QUANTIZATION ON BERT
https://pytorch.org/tutorials/intermediate/dynamic_quantization_bert_tutorial.html

 

Quantization in Deep Learning
https://medium.com/@joel_34050/quantization-in-deep-learning-478417eab72b

 

QUANTIZATION
https://pytorch.org/docs/stable/quantization.html

 

[DL] Optimization Techniques
https://talkingaboutme.tistory.com/entry/DL-Optimization-Techniques

 

Quantization-aware training에 대한 code 정리
https://wannabeaprogrammer.tistory.com/42

 

PyTorch Quantization Aware Training
https://leimao.github.io/blog/PyTorch-Quantization-Aware-Training/

 

Quantization
https://velog.io/@ganta/Quantization

 

[Embedded][DL] Tensorflow Lite - Quantization
https://talkingaboutme.tistory.com/entry/Embedded-DL-Tensorflow-Lite-Quantization

 

[Day39] 양자화 & 지식 증류
https://n-brogrammer.tistory.com/135

 

Post-training quantization
https://www.tensorflow.org/lite/performance/post_training_quantization

 

Natural Language Processing with Transformers
https://huggingface.co/transformersbook

 

 

Show, Attend and Tell : Image Captioning에서 Soft Attention, Hard Attention
https://ahjeong.tistory.com/8

 

Show, Attend and Tell: Neural Image Caption Generation With Visual Attention (ICML2015)
http://sanghyukchun.github.io/93/