Top 61 model-compression open source projects

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

Infrastructures™ for Machine Learning Training/Inference in Production.

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

A pytorch pruning toolkit for structured neural network pruning and layer dependency maintaining.

Java interface for fastText

Deep Face Model Compression

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

Awesome machine learning model compression research papers, tools, and learning material.

Model Compression CLI Tool for Keras.

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019) and "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020).

PyTorch Implementation of Weights Pruning

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

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

yolov3 by pytorch

PyTorch code for our CVPR'20 paper "Collaborative Distillation for Ultra-Resolution Universal Style Transfer"

Programmable Neural Network Compression

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

MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images

papers about model compression

An Open Source Deep Learning Inference Engine Based on FPGA

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

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

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

The Easiest Knowledge Distillation Library for Lightweight Deep Learning

Model Compression Based on Geoffery Hinton's Logit Regression Method in Keras applied to MNIST 16x compression over 0.95 percent accuracy.An Implementation of "Distilling the Knowledge in a Neural Network - Geoffery Hinton et. al"

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

A curated list of neural network pruning resources.

Compressing Representations for Self-Supervised Learning

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

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

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

This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

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.

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

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.

Pytorch implementation of various Knowledge Distillation (KD) methods.

[CVPR2020] GhostNet: More Features from Cheap Operations

knowledge distillation papers

Data Efficient Model Compression

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

[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

[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

It is a blueprint to data science from the mathematics to algorithms. It is not completed.

Deep Learning for Computer Vision (CommE 5052) in NTU

Efficient-Computing

Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据

🤖 A machine learning framework for audio, text, image, video, or .CSV files (50+ featurizers and 15+ model trainers).

[ICLR'21] PyTorch code for our paper "Neural Pruning via Growing Regularization"

Learnable Embedding Space for Efficient Neural Architecture Compression

[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

pytorch realtime multi person keypoint estimation

pytorch implementation of Structured Bayesian Pruning

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

Automatic DNN compression tool with various model compression and neural architecture search techniques