Top 81 quantization open source projects

[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision

Bring Deep Learning to small devices

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Infrastructures™ for Machine Learning Training/Inference in Production.

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

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

Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

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

Ternary Gradients to Reduce Communication in Distributed Deep Learning (TensorFlow)

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

PyTorch Model Compression

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

A PyTorch implementation of "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"

Quantization of Convolutional Neural networks.

Fast inference engine for OpenNMT models

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

Graph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow

PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.

Collections of model quantization algorithms

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.

Reducing the size of convolutional neural networks

FrostNet: Towards Quantization-Aware Network Architecture Search

Powerful, automated analysis and design of quantum microwave chips & devices [Energy-Participation Ratio and more]

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

Dice.com repo to accompany the dice.com 'Vectors in Search' talk by Simon Hughes, from the Activate 2018 search conference, and the 'Searching with Vectors' talk from Haystack 2019 (US). Builds upon my conceptual search and semantic search work from 2015

pytorch implementation of "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks"

reference pytorch code for named entity tagging

Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models

Simulate quantization and quantization aware training for MXNet-Gluon models.

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

SDK for TEE AI Stick (includes model training script, inference library, examples)

Trainable models and NN optimization tools

libimagequant (pngquant) bindings for the Rust language

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.

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

A treasure chest for image classification powered by PaddlePaddle

Embedded and mobile deep learning research resources

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

An Open-Source Package for Deep Learning to Hash (DeepHash)

Lossy PNG compressor — pngquant command based on libimagequant library

Brevitas: quantization-aware training in PyTorch

Palette quantization library that powers pngquant and other PNG optimizers

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

Must-read papers on deep learning to hash (DeepHash)

Dataflow compiler for QNN inference on FPGAs

QKeras: a quantization deep learning library for Tensorflow Keras

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

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

🎨 Simple color palette quantization using MMCQ

Go library for color quantization and dithering

Pruning and quantization for SSD. Model compression.

The implementation of AAAI-17 paper "Collective Deep Quantization of Efficient Cross-modal Retrieval"

KGy SOFT Drawing is a library for advanced image, icon and graphics handling.

Repository containing code for "U-Net Fixed-Point Quantization for Medical Image Segmentation" paper at MICCAI2019

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

TensorFlow Quantization Example, for TensorFlow Lite

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

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