60 Open source projects that are alternatives of or similar to Aquvitae

A pytorch pruning toolkit for structured neural network pruning and layer dependency maintaining.

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Efficient-Computing

(CVPR 2021, Oral) Dynamic Slimmable Network

An Open Source Deep Learning Inference Engine Based on FPGA

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

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

Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.

Programmable Neural Network Compression

Learnable Embedding Space for Efficient Neural Architecture Compression

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Infrastructures™ for Machine Learning Training/Inference in Production.

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.

Deep Face Model Compression

It is a blueprint to data science from the mathematics to algorithms. It is not completed.

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019) and "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020).

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

yolov3 by pytorch

🤖 A machine learning framework for audio, text, image, video, or .CSV files (50+ featurizers and 15+ model trainers).

MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images

[CVPR2020] GhostNet: More Features from Cheap Operations

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

pytorch realtime multi person keypoint estimation

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

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

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

Automatic DNN compression tool with various model compression and neural architecture search techniques

This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

Papers for deep neural network compression and acceleration

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).

Compressing Representations for Self-Supervised Learning

Java interface for fastText

[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

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

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

Model Compression CLI Tool for Keras.

Deep Learning for Computer Vision (CommE 5052) in NTU

PyTorch Implementation of Weights Pruning

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

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

PyTorch code for our CVPR'20 paper "Collaborative Distillation for Ultra-Resolution Universal Style Transfer"

Pytorch implementation of various Knowledge Distillation (KD) methods.

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

[ICLR'21] PyTorch code for our paper "Neural Pruning via Growing Regularization"

papers about model compression

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

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

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

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

knowledge distillation papers

pytorch implementation of Structured Bayesian Pruning

Model Compression Based on Geoffery Hinton's Logit Regression Method in Keras applied to MNIST 16x compression over 0.95 percent accuracy.An Implementation of "Distilling the Knowledge in a Neural Network - Geoffery Hinton et. al"

A curated list of neural network pruning resources.

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

Data Efficient Model Compression

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