140 Open source projects that are alternatives of or similar to ZAQ-code

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

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

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

Infrastructures™ for Machine Learning Training/Inference in Production.

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

An Open Source Deep Learning Inference Engine Based on FPGA

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

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

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

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

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.

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

Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据

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

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

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

reference pytorch code for named entity tagging

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

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

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

Trainable models and NN optimization tools

Quantization of Convolutional Neural networks.

libimagequant (pngquant) bindings for the Rust language

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.

A treasure chest for image classification powered by PaddlePaddle

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

PyTorch Model Compression

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

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

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

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

TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.

(CVPR 2021, Oral) Dynamic Slimmable Network

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

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

Lossy PNG compressor — pngquant command based on libimagequant library

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]

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

Embedded and mobile deep learning research resources

Graph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow

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

Code and Data for paper: Zero-shot Visual Question Answering using Knowledge Graph [ ISWC 2021 ]

Brevitas: quantization-aware training in PyTorch

Collections of model quantization algorithms

Palette quantization library that powers pngquant and other PNG optimizers

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

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

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

Reducing the size of convolutional neural networks

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

FrostNet: Towards Quantization-Aware Network Architecture Search

Go library for color quantization and dithering

Pruning and quantization for SSD. Model compression.

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

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

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