Topic: model-compression Goto Github

👇 Here are 246 public repositories matching this topic...

1duo / awesome-ai-infrastructures
model-compression,Infrastructures™ for Machine Learning Training/Inference in Production.
User: 1duo
artificial-intelligence machine-learning deep-learning machine-learning-systems awesome-list deep-learning-framework kubernetes apache-spark apache-arrow apache-mesos

666dzy666 / micronet
model-compression,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
User: 666dzy666
quantization pruning dorefa twn bnn xnor-net pytorch model-compression group-convolution network-slimming

aberhu / knowledge-distillation-zoo
model-compression,Pytorch implementation of various Knowledge Distillation (KD) methods.
User: aberhu
kd-methods knowledge-transfer knowledge-distillation kd teacher-student model-compression distillation

alibaba / tinyneuralnetwork
model-compression,TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
Organization: alibaba
pytorch deep-learning model-compression pruning model-converter quantization-aware-training deep-neural-networks post-training-quantization

cedrickchee / awesome-ml-model-compression
model-compression,Awesome machine learning model compression research papers, quantization, tools, and learning material.
User: cedrickchee
machine-learning model-compression quantization pruning awesome-list neural-networks

changlin31 / ds-net
model-compression,(CVPR 2021, Oral) Dynamic Slimmable Network
User: changlin31
dynamic-networks pruning network-pruning dynamic-pruning model-compression efficient-inference

chester256 / model-compression-papers
model-compression,Papers for deep neural network compression and acceleration
User: chester256
deep-learning model-compression papers deep-neural-networks model-acceleration

cnkuangshi / lightctr
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.
User: cnkuangshi
machine-learning deep-learning factorization-machines distributed-systems parameter-server model-compression computational-graphs

czg1225 / slimsam
model-compression,SlimSAM: 0.1% Data Makes Segment Anything Slim
User: czg1225
knowledge-distillation model-compression model-pruning segment-anything-model

dkozlov / awesome-knowledge-distillation
model-compression,Awesome Knowledge Distillation
User: dkozlov
knowledge-distillation knowledge-transfer teacher-student co-training distillation distillation-model model-distillation knowldge-distillation kd model-compression

ethanhe42 / channel-pruning
model-compression,Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
User: ethanhe42
Home Page: https://arxiv.org/abs/1707.06168
image-recognition model-compression acceleration object-detection image-classification channel-pruning deep-neural-networks

flhonker / awesome-knowledge-distillation
model-compression,Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。
User: flhonker
kd knowldge-distillation distillation deep-learning transfer-learning model-compression

guan-yuan / awesome-automl-and-lightweight-models
model-compression,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.
User: guan-yuan
automl meta-learning automated-feature-engineering hyperparameter-optimization architecture-search model-compression model-acceleration awesome-list neural-architecture-search nas

haitongli / knowledge-distillation-pytorch
model-compression,A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
User: haitongli
pytorch knowledge-distillation deep-neural-networks cifar10 model-compression dark-knowledge computer-vision

he-y / awesome-pruning
model-compression,A curated list of neural network pruning resources.
User: he-y
pruning model-compression model-acceleration awesome-list

he-y / filter-pruning-geometric-median
model-compression,Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)
User: he-y
Home Page: https://arxiv.org/abs/1811.00250
pruning pytorch model-compression

he-y / soft-filter-pruning
model-compression,Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
User: he-y
Home Page: https://arxiv.org/abs/1808.06866
pruning pytorch model-compression

horseee / deepcache
model-compression,[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
User: horseee
Home Page: https://horseee.github.io/Diffusion_DeepCache/
diffusion-models efficient-inference model-compression stable-diffusion training-free

hoytta0 / knowledgedistillation
model-compression,Knowledge distillation in text classification with pytorch. 知识蒸馏，中文文本分类，教师模型BERT、XLNET，学生模型biLSTM。
User: hoytta0
knowledge-distillation bert pytorch model-compression distillation

htqin / awesome-model-quantization
model-compression,A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.
User: htqin
deep-learning quantization awesome model-compression binarization binarized-neural-networks binary-network efficient-deep-learning lightweight-neural-network model-acceleration

huawei-noah / efficient-ai-backbones
model-compression,Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
Organization: huawei-noah
convolutional-neural-networks efficient-inference imagenet model-compression tensorflow pytorch ghostnet transformer pretrained-models vision-transformer

huawei-noah / efficient-computing
model-compression,Efficient computing methods developed by Huawei Noah's Ark Lab
Organization: huawei-noah
knowledge-distillation model-compression binary-neural-networks pruning quantization self-supervised

huawei-noah / pretrained-language-model
model-compression,Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Organization: huawei-noah
knowledge-distillation model-compression quantization pretrained-models large-scale-distributed

iamhankai / ghostnet.pytorch
model-compression,[CVPR2020] GhostNet: More Features from Cheap Operations
User: iamhankai
Home Page: https://arxiv.org/abs/1911.11907
convolutional-neural-networks mobilenetv3 model-compression pytorch fbnet

jetrunner / bert-of-theseus
model-compression,⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).
User: jetrunner
bert transformers nlp glue model-compression

kssteven418 / i-bert
model-compression,[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
User: kssteven418
Home Page: https://arxiv.org/abs/2101.01321
natural-language-processing quantization efficient-model efficient-neural-networks transformer bert model-compression

lhyfst / knowledge-distillation-papers
model-compression,knowledge distillation papers
User: lhyfst
dark-knowledge knowledge-distillation model-compression paper reading-list

liuziwei7 / mobile-id
model-compression,Deep Face Model Compression
User: liuziwei7
Home Page: http://personal.ie.cuhk.edu.hk/~lz013/projects/MobileID.html
computer-vision deep-learning face-recognition model-compression efficient-inference

microsoft / archai
model-compression,Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
Organization: microsoft
Home Page: https://microsoft.github.io/archai
python pytorch machine-learning deep-learning neural-architecture-search nas automated-machine-learning model-compression darts petridish

microsoft / neuronblocks
model-compression,NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego
Organization: microsoft
question-answering deep-learning pytorch natural-language-processing text-classification artificial-intelligence dnn qna text-matching knowledge-distillation

microsoft / nni
model-compression,An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Organization: microsoft
Home Page: https://nni.readthedocs.io
automl deep-learning neural-architecture-search hyperparameter-optimization distributed bayesian-optimization automated-machine-learning machine-learning machine-learning-algorithms data-science

mingsun-tse / efficient-deep-learning
model-compression,Collection of recent methods on (deep) neural network compression and acceleration.
User: mingsun-tse
model-compression network-pruning knowledge-distillation deep-learning deep-neural-networks efficient-deep-learning

mit-han-lab / amc
model-compression,[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Organization: mit-han-lab
Home Page: https://arxiv.org/abs/1802.03494
automl automl-for-compression channel-pruning efficient-model model-compression on-device-ai

peterisfar / yolov3
model-compression,yolov3 by pytorch
User: peterisfar
yolov3 pytorch voc object-detection model-compression mobilenetv2

pratyushasharma / laser
model-compression,The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
User: pratyushasharma
Home Page: https://pratyushasharma.github.io/laser/
gpt-j interpretability laser llama2 llm llms model-compression transformers

sforaidl / kd_lib
model-compression,A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Organization: sforaidl
Home Page: https://kd-lib.readthedocs.io/
algorithm-implementations benchmarking data-science deep-learning-library knowledge-distillation machine-learning model-compression pruning pytorch quantization

sharpiless / yolov5-distillation-train-inference
model-compression,Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据
User: sharpiless
yolov5 distillation object-detection model-compression konwledge-distillation

squeezeailab / kvquant
model-compression,KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Organization: squeezeailab
Home Page: https://arxiv.org/abs/2401.18079
compression efficient-inference efficient-model large-language-models llama llm localllama localllm mistral model-compression

squeezeailab / squeezellm
model-compression,[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Organization: squeezeailab
Home Page: https://arxiv.org/abs/2306.07629
efficient-inference large-language-models llm model-compression natural-language-processing post-training-quantization quantization text-generation transformer llama

sunshangquan / logit-standardization-kd
model-compression,[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation
User: sunshangquan
computer-vision cv cvpr cvpr2024 knowledge-distillation model-compression resnet vision-transformer

tencent / pocketflow
model-compression,An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Organization: tencent
Home Page: https://pocketflow.github.io
deep-learning model-compression mobile-app automl computer-vision

tensorflow / model-optimization
model-compression,A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Organization: tensorflow
Home Page: https://www.tensorflow.org/model_optimization
tensorflow machine-learning deep-learning optimization quantized-neural-networks quantized-networks quantized-training keras model-compression compression

thu-mig / torch-model-compression
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
Organization: thu-mig
pruning quantization-aware-training tensorrt-conversion tensorrt model-compression acnet reparameterization pytorch onnx quantization

tianyic / only_train_once
model-compression,OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM
User: tianyic
pytorch deep-learning model-compression sparse-optimization pruning automl one-shot training erasing-operators

vainf / torch-pruning
model-compression,[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
User: vainf
Home Page: https://arxiv.org/abs/2301.12900
channel-pruning cvpr2023 depgraph efficient-deep-learning model-compression network-pruning pruning structural-pruning structured-pruning

vinhkhuc / jfasttext
model-compression,Java interface for fastText
User: vinhkhuc
machine-learning nlp java word-embeddings jni text-classification model-compression

xiuyu-li / q-diffusion
model-compression,[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
User: xiuyu-li
Home Page: https://xiuyuli.com/qdiffusion/
diffusion-models quantization ddim pytorch stable-diffusion model-compression post-training-quantization

yehuitang / pruning
model-compression,Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019), "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020) and “Manifold Regularized Dynamic Network Pruning” (CVPR 2021).
User: yehuitang
network-pruning model-compression

zhen-dong / awesome-quantization-papers
model-compression,List of papers related to neural network quantization in recent AI conferences and journals.
User: zhen-dong
quantization awesome-list papers neural-networks model-compression edge-computing efficient-inference diffusion-models large-language-models

zhen-dong / hawq
model-compression,Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
User: zhen-dong
quantization tvm model-compression distillation quantized-neural-networks pytorch hardware-aware mixed-precision efficient-neural-networks 8-bit