Lossy PNG compressor — pngquant command based on libimagequant library

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

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

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

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

model compression based on pytorch (1、quantization: 16/8/4/2 bits(dorefa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for quantization)

Trainable models and NN optimization tools

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.

Embedded and mobile deep learning research resources

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

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

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

Palette quantization library that powers pngquant and other PNG optimizers

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

Brevitas: quantization-aware training in Pytorch

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

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. OpenVINO.

QKeras: a quantization deep learning library for Tensorflow Keras

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

Infrastructures™ for Machine Learning Training/Inference in Production.

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

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

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

Quantization of Convolutional Neural networks.

Graph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow.

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

Collections of model quantization algorithms

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

Reducing the size of convolutional neural networks