60 Open source projects that are alternatives of or similar to Bert Of Theseus

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

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

The Easiest Knowledge Distillation Library for Lightweight Deep Learning

Pytorch implementation of various Knowledge Distillation (KD) methods.

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

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

[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

yolov3 by pytorch

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

Compressing Representations for Self-Supervised Learning

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

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

An Open Source Deep Learning Inference Engine Based on FPGA

knowledge distillation papers

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

Papers for deep neural network compression and acceleration

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

Deep Learning for Computer Vision (CommE 5052) in NTU

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

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

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

pytorch implementation of Structured Bayesian Pruning

Programmable Neural Network Compression

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

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

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.

Infrastructures™ for Machine Learning Training/Inference in Production.

papers about model compression

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.

PyTorch Implementation of Weights Pruning

[CVPR2020] GhostNet: More Features from Cheap Operations

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

Data Efficient Model Compression

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

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

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

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

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

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

Efficient-Computing

Java interface for fastText

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

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"

Learnable Embedding Space for Efficient Neural Architecture Compression

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

pytorch realtime multi person keypoint estimation

A curated list of neural network pruning resources.

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

Model Compression CLI Tool for Keras.

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

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

(CVPR 2021, Oral) Dynamic Slimmable Network

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

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

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

Deep Face Model Compression

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

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

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