Papers with Code 아카이브

Model Compression

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 1
평가표: 2
보존된 평가 기록: 14

Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Mind23-2/MindCode-172

Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks

https://github.com/Mind23-2/MindCode-80

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/MindSpore-paper-code-3/code6/tree/main/advanced_east

DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

https://github.com/MindSpore-scientific/code-11/tree/main/Patient2Vec-A-Personalized-Interpretable

Patient Knowledge Distillation for BERT Model Compression

https://github.com/MindSpore-scientific/code-13/tree/main/Patient2Vec-A-Personalized-Interpretable

Patient Knowledge Distillation for BERT Model Compression

https://github.com/MrRen-sdhm/Embedded_Multi_Object_Detection_CNN

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/NatGr/Master_Thesis

A Closer Look at Structured Pruning for Neural Network Compression

https://github.com/PAIR-code/lit

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/PaddlePaddle/PaddleClas

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/PanQiWei/AutoGPTQ

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

https://github.com/Qengineering/SqueezeNet-ncnn

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/Qualcomm-AI-research/Skip-Conv

Skip-Convolutions for Efficient Video Processing

https://github.com/RAIVNLab/STR

To prune, or not to prune: exploring the efficacy of pruning for model compression

https://github.com/RenXiangyuan/tf_bert

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/SLDGroup/NN_Mass

How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?

https://github.com/SauravMaheshkar/Compressed-DNNs-Forget

What Do Compressed Deep Neural Networks Forget?

https://github.com/ShawnDing1994/ACNet

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

https://github.com/ShawnDing1994/AOFP

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

https://github.com/ShawnDing1994/Centripetal-SGD

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

https://github.com/Shiweiliuiiiiiii/GraNet

The State of Sparsity in Deep Neural Networks

https://github.com/Shunli-Wang/Tiny-YOLO-LSQ

Learned Step Size Quantization

https://github.com/SpikeKing/My-Bert

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/StoneGH/bert

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/TonyX19/bert_hyperpartisan

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/VeritasXu/Ternary-Federated

Ternary Weight Networks

https://github.com/Walter-B/bert-20-classes

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/WilliamLiPro/LpSS

The State of Sparsity in Deep Neural Networks

https://github.com/XINZXZHANG/Bert_repo

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/XJTUWYD/TWN

Ternary Weight Networks

https://github.com/YOUSIKI/PyTorch-FBS

Dynamic Channel Pruning: Feature Boosting and Suppression

https://github.com/ZTao-z/ProxylessNAS

AMC: AutoML for Model Compression and Acceleration on Mobile Devices

https://github.com/ZouJiu1/LSQplus

Learned Step Size Quantization

https://github.com/abhiagg92/bert_sentiment

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

https://github.com/adeely9/experiment_2_python3

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

https://github.com/akashrajkn/waffles-and-posteriors

Soft Weight-Sharing for Neural Network Compression

https://github.com/amazon-science/dq-bart

DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.