577 Open source projects that are alternatives of or similar to SSD-Pruning-and-quantization

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

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

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

PyTorch Model Compression

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

Embedded and mobile deep learning research resources

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

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

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

🔌⚡ 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

Trainable models and NN optimization tools

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

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

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

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.

Repository to track the progress in model compression and acceleration

reference pytorch code for named entity tagging

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

Prunable nn layers for pytorch.

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

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

Collections of model quantization algorithms

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

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

Implement of Dynamic Model Pruning with Feedback with pytorch

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

Infrastructures™ for Machine Learning Training/Inference in Production.

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

All about acceleration and compression of Deep Neural Networks

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

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

very simple LZ77-based compression

A Rust library for Huffman compression given a propability distribution over arbitrary symbols

FEMU: Accurate, Scalable and Extensible NVMe SSD Emulator (FAST'18)

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

An extension which allows you to easily compress your Sanic responses with gzip.

An implementation of a DEFLATE encoder in rust

TensorFlow Quantization Example, for TensorFlow Lite

A simple lightweight set of implementations and bindings for compression algorithms written in Go.

Windows application to send TRIM / UNMAP / DISCARD to SSD. Similar to blkdiscard.

Perform inferencing of tensorflow-lite models on an RPi with acceleration from Coral USB stick

Autoencoder based image compression: can the learning be quantization independent? https://arxiv.org/abs/1802.09371

Sequitur and RePair grammar induction algorithms implementation

Django middleware that compresses response using brotli algorithm.

Box - Open Standard Archive Format, a zip killer.

Tiny unzip helper class for .NET 3.5 Client Profile and Mono 2.10, written in pure C#.

Universal way for ignoring unnecessary common files to fit your bundle

Ruby's missing background and batch processing system

🗜️ Deno HTTP compression middleware

OpenMMLab Model Compression Toolbox and Benchmark.

The lightweight library for compress image, video, and audio with an awesome experience

x – minimalist data compressor

Single Shot MultiBox Detector(SSD)目标检测算法

Make app thinner. Help you find large files and compress png, gif, jpg, svg files. 应用程序瘦身工具，帮助你找到大文件，压缩png、gif、jpg、svg等文件。

Node.js cross-platform wrapper for UPX - the ultimate packer for eXecutables.

A simplified implementation of the LZ77 compression algorithm

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

A library for secure, deduplicated, transactional, and verifiable data storage

Attempting feature map prunning on a CNN trained for Japanese OCR

LittleBit is a pure Huffman coding compression algorithm with the option of random access reading while offering competitive compression ratios.