模型压缩资料积累

深度学习的模型压缩可能就是自己硕士阶段的研究课题啦，这篇博客记录在学习过程中遇到的比较好的资料，作为积累和备忘。

github awesome collections

• htqin/awesome-model-quantization
  • A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research.
• csyhhu/Awesome-Deep-Neural-Network-Compression
  • Summary, Code for Deep Neural Network Quantization
• chester256/Model-Compression-Papers
  • Papers for deep neural network compression and acceleration
• juliagusak/model-compression-and-acceleration-progress
• he-y/Awesome-Pruning
  • A curated list of neural network pruning resources.
• FLHonker/Awesome-Knowledge-Distillation
  • Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

github project repo

• IntelLabs/distiller
  • Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research.

• j-marple-dev/model_compression

• lucamocerino/Binary-Neural-Networks-PyTorch-1.0
  • BNNs (XNOR, BNN and DoReFa) implementation for PyTorch 1.0+
• jiecaoyu/XNOR-Net-PyTorch

• 666DZY666/micronet

  • 可供模型压缩加速入门参考
• JDAI-CV/dabnn
• dabnn is an accelerated binary neural networks inference framework for mobile platform

• flame/how-to-optimize-gemm

  • A step-by-step gemm optimization tutorial

Attractive blogs

量化

• 二值化神经网络(BNN)综述 - Ironboy的文章 - 知乎
• 神经网络模型量化方法简介

• 模型压缩算法汇总

• Making Neural Nets Work With Low Precision

• Compression and Acceleration of High-dimensional Neural Networks
• distiller - 非对称量化和对称量化的理论推导
• NVIDIA Deep Learning Performance Documentation ——英伟达yyds!
• 闲话模型压缩之量化（Quantization）篇
• Anatomy of a High-Speed Convolution

剪枝

• 论文总结 - 模型剪枝 Model Pruning

• 闲话模型压缩之网络剪枝（Network Pruning）篇

• https://www.yuque.com/yahei/hey-yahei/opsummary.mxnet)

• https://segmentfault.com/a/1190000020993594)

BiliBili

量化

• 神经网络量化 BiliBili code

• Google Developer Days - 模型优化与量化

• 哈佛大学在读博士董鑫：模型量化—更小更快更强