1199 Open source projects that are alternatives of or similar to Model Optimization

Infrastructures™ for Machine Learning Training/Inference in Production.

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

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

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

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

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

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference

Pruning and quantization for SSD. Model compression.

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

Pytorch implementation of our CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

Python Geohash Compression Tool

Mesh optimization library that makes meshes smaller and faster to render

A curated list of neural network pruning resources.

reference pytorch code for named entity tagging

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

An Open Source Deep Learning Inference Engine Based on FPGA

PyTorch Model Compression

A curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

Collections of model quantization algorithms

A research library for pytorch-based neural network pruning, compression, and more.

Prunable nn layers for pytorch.

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

All about acceleration and compression of Deep Neural Networks

Image conversion and optimization desktop app.

Heavily optimized zlib compression algorithm

Repository to track the progress in model compression and acceleration

CSS Optimizer(csso) ruby wrapper for Rails Asset pipeline

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

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

A Webpack boilerplate for static websites that has all the necessary modern tools and optimizations built-in. Score a perfect 10/10 on performance.

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

K-Means clustering - constrained with minimum and maximum cluster size

[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

Smart image optimization

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

The Caesium compression library written in Rust

Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint

(CVPR 2021, Oral) Dynamic Slimmable Network

Open-source implementation of Google Vizier for hyper parameters tuning

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

FasterAI: A repository for making smaller and faster models with the FastAI library.

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

Data compression in TensorFlow

Embedded and mobile deep learning research resources

🔌⚡ Nuxt module to prune html before sending it to the browser (it removes elements matching CSS selector(s)), useful for boosting performance showing a different HTML for bots/audits by removing all the scripts with dynamic rendering

[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

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

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

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

Automated image compression for efficiently distributing images on the web.

Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries

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.

A Github Action that automatically compresses JPEGs, PNGs and WebPs in Pull Requests.

Simple image compression full website code written in node, react and next.js framework. Easy to deploy as a microservice.

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.