Papers with Code 아카이브
Model Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/modelhub-ai/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mtmd/Mobile_ConvNet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/munjalbharti/Knowledge-Distillation-for-End-to-End-Person-Search
https://github.com/musco-ai/musco-pytorch
https://github.com/musco-ai/musco-tf
https://github.com/mzymzy/paper3-quantized_distillzation
https://github.com/newwhitecheng/compress-all-nn
Differentiable Fine-grained Quantization for Deep Neural Network Compression
https://github.com/ningchihuang/ELSA
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
https://github.com/nobug-code/Diversity_Networks_CNN_Pytorch
Diversity Networks: Neural Network Compression Using Determinantal Point Processes
https://github.com/ofsoundof/Heterogeneity_Hypothesis
Learning Filter Basis for Convolutional Neural Network Compression
https://github.com/ofsoundof/group_sparsity
Learning Filter Basis for Convolutional Neural Network Compression
https://github.com/osmr/imgclsmob
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/p0werweirdo/tagfcl
Compacting, Picking and Growing for Unforgetting Continual Learning
https://github.com/paolanu/BERT_epitope
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/philipco/artemis-bidirectional-compression
Preserved central model for faster bidirectional compression in distributed settings
https://github.com/pingheng001/Cnn-Bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/pra-dan/Worth-Reading-ML-Papers
https://github.com/pwc-1/Paper-9/tree/main/lxmert
https://github.com/pyf98/dphubert
Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding
https://github.com/pytorch/vision
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/quantumiracle/Cascading-Decision-Tree
https://github.com/qwopqwop200/GPTQ-for-LLaMa
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/rasmith/vllm
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/rcmalli/keras-squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/ricardordb/bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/ricky40403/GDFQ
https://github.com/rishikksh20/LightSpeech
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
https://github.com/robinreni96/Font_Recognition-DeepFont
https://github.com/rohan400/PepperQA
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/safe-rl-team/viper-verifiable-rl-impl
https://github.com/saintslab/pepr
https://github.com/sdc17/crossget
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
https://github.com/senya-ashukha/variational-dropout-sparsifies-dnn
https://github.com/seo3650/Contrastive_Representation_Distillation
https://github.com/seulkiyeom/once-for-all
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.