https://github.com/softsys4ai/neural-distiller
Play and Prune: Adaptive Filter Pruning for Deep Model Compression
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/somiltg/bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/songhan/DSD
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
https://github.com/songhan/SqueezeNet-Deep-Compression
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/songhan/SqueezeNet-Residual
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
https://github.com/taltole/CIFAR10_SqueezeNet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/taltole/LiteNetwork_Image_Classification
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/temibabs/data-free-adversarial-distillation
https://github.com/thaarres/Quantized_CNN
https://github.com/the-Quert/iNLPfun
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/theQuert/inlpfun
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/thecodemasterk/BERT
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/thousandvoices/ok_ml_cup
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/thudm/chatglm-6b
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/tophatraptor/si-transfer
Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
https://github.com/unimodal4reasoning/adaptivediffusion
Performance-aware Approximation of Global Channel Pruning for Multitask CNNs
https://github.com/vectorch-ai/scalellm
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/vibhu444/alexnet-squeeze-mnist
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/vicontek/lrbtnn
Bayesian Tensorized Neural Networks with Automatic Rank Selection
https://github.com/vita-group/atmc
Model Compression with Adversarial Robustness: A Unified Optimization Framework
https://github.com/vita-group/granet
https://github.com/vllm-project/vllm
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/vonclites/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/wgao9/weight_quant
Information-Theoretic Understanding of Population Risk Improvement with Model Compression
https://github.com/xiaopp123/bert_explain
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/xin-w8023/SqueezeNet-PyTorch
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/xitianxiaofeixue/BERT
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/xvyaward/owq
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/yangyucheng000/Paper-3/tree/main/SharpDRO-ms
https://github.com/yuchaoli/CC
https://github.com/yuhangT/tf_bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/zejiangh/Filter-GaP
https://github.com/zejiangh/Multi-dimensional-vit-compression
https://github.com/zhanhuijing/ECC_PYCHARM
https://github.com/zhutmost/lsq-net
https://github.com/zjZSTU/LightWeightCNN
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.