AimetAIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Stars: ✭ 453 (+2284.21%)
Model OptimizationA toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Stars: ✭ 992 (+5121.05%)
NncfPyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference
Stars: ✭ 218 (+1047.37%)
Micronetmicronet, 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
Stars: ✭ 1,232 (+6384.21%)
Awesome EmdlEmbedded and mobile deep learning research resources
Stars: ✭ 554 (+2815.79%)
torchpruneA research library for pytorch-based neural network pruning, compression, and more.
Stars: ✭ 133 (+600%)
sparsezooNeural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Stars: ✭ 264 (+1289.47%)
DistillerNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Stars: ✭ 3,760 (+19689.47%)
nuxt-prune-html🔌⚡ 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
Stars: ✭ 69 (+263.16%)
Awesome Edge Machine LearningA curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.
Stars: ✭ 139 (+631.58%)
Zeroq[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework
Stars: ✭ 150 (+689.47%)
Lq NetsLQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Stars: ✭ 195 (+926.32%)
neural-compressorIntel® 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.
Stars: ✭ 666 (+3405.26%)
Ntaggerreference pytorch code for named entity tagging
Stars: ✭ 58 (+205.26%)
sparsifyEasy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
Stars: ✭ 138 (+626.32%)
Awesome Ml Model CompressionAwesome machine learning model compression research papers, tools, and learning material.
Stars: ✭ 166 (+773.68%)
Kd libA Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Stars: ✭ 173 (+810.53%)
HrankPytorch implementation of our CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map
Stars: ✭ 164 (+763.16%)
fasterai1FasterAI: A repository for making smaller and faster models with the FastAI library.
Stars: ✭ 34 (+78.95%)
PaddleslimPaddleSlim is an open-source library for deep model compression and architecture search.
Stars: ✭ 677 (+3463.16%)
DNNACAll about acceleration and compression of Deep Neural Networks
Stars: ✭ 29 (+52.63%)
ATMC[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”
Stars: ✭ 41 (+115.79%)
bert-squeeze🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
Stars: ✭ 56 (+194.74%)
zpackervery simple LZ77-based compression
Stars: ✭ 15 (-21.05%)
rust-huffman-compressA Rust library for Huffman compression given a propability distribution over arbitrary symbols
Stars: ✭ 18 (-5.26%)
FEMUFEMU: Accurate, Scalable and Extensible NVMe SSD Emulator (FAST'18)
Stars: ✭ 213 (+1021.05%)
optimum🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools
Stars: ✭ 567 (+2884.21%)
sanic compressAn extension which allows you to easily compress your Sanic responses with gzip.
Stars: ✭ 26 (+36.84%)
deflate-rsAn implementation of a DEFLATE encoder in rust
Stars: ✭ 47 (+147.37%)
raisinA simple lightweight set of implementations and bindings for compression algorithms written in Go.
Stars: ✭ 17 (-10.53%)
disktrimWindows application to send TRIM / UNMAP / DISCARD to SSD. Similar to blkdiscard.
Stars: ✭ 17 (-10.53%)
coral-pi-rest-serverPerform inferencing of tensorflow-lite models on an RPi with acceleration from Coral USB stick
Stars: ✭ 49 (+157.89%)
GISequitur and RePair grammar induction algorithms implementation
Stars: ✭ 20 (+5.26%)
django-brotliDjango middleware that compresses response using brotli algorithm.
Stars: ✭ 16 (-15.79%)
boxBox - Open Standard Archive Format, a zip killer.
Stars: ✭ 38 (+100%)
unzipTiny unzip helper class for .NET 3.5 Client Profile and Mono 2.10, written in pure C#.
Stars: ✭ 25 (+31.58%)
untrackedUniversal way for ignoring unnecessary common files to fit your bundle
Stars: ✭ 26 (+36.84%)
rocketjobRuby's missing background and batch processing system
Stars: ✭ 281 (+1378.95%)
mmrazorOpenMMLab Model Compression Toolbox and Benchmark.
Stars: ✭ 644 (+3289.47%)
react-native-compressorThe lightweight library for compress image, video, and audio with an awesome experience
Stars: ✭ 157 (+726.32%)
x-compressorx – minimalist data compressor
Stars: ✭ 42 (+121.05%)
SSD KerasSingle Shot MultiBox Detector(SSD)目标检测算法
Stars: ✭ 44 (+131.58%)
AppThinningMake 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。
Stars: ✭ 22 (+15.79%)
upxNode.js cross-platform wrapper for UPX - the ultimate packer for eXecutables.
Stars: ✭ 27 (+42.11%)
LZ77-CompressorA simplified implementation of the LZ77 compression algorithm
Stars: ✭ 70 (+268.42%)
ppqPPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Stars: ✭ 281 (+1378.95%)
acid-storeA library for secure, deduplicated, transactional, and verifiable data storage
Stars: ✭ 48 (+152.63%)
jp-ocr-prunned-cnnAttempting feature map prunning on a CNN trained for Japanese OCR
Stars: ✭ 15 (-21.05%)
LittleBitLittleBit is a pure Huffman coding compression algorithm with the option of random access reading while offering competitive compression ratios.
Stars: ✭ 13 (-31.58%)