model-compression

Awesome Knowledge Distillation

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

A curated list of neural network pruning resources.

NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

PaddleSlim is an open-source library for deep model compression and architecture search.

Pytorch implementation of various Knowledge Distillation (KD) methods.

A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.

Collection of recent methods on (deep) neural network compression and acceleration.

Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.

Structural Pruning for Model Acceleration

knowledge distillation papers

[CVPR2020] GhostNet: More Features from Cheap Operations

Efficient-Computing

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

Archai accelerates Neural Architecture Search (NAS) through fast, reproducible and modular research.

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Papers for deep neural network compression and acceleration

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

Infrastructures™ for Machine Learning Training/Inference in Production.

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).