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/johngear/eecs504
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/jongwooko/nash-pruning-official
https://github.com/keonlee9420/DiffSinger
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
https://github.com/kingcong/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/kinshukdua/FedUKD
https://github.com/klieberman/ood_nic
To prune, or not to prune: exploring the efficacy of pruning for model compression
https://github.com/kpaupamah/compression-and-regularisation
Quantisation and Pruning for Neural Network Compression and Regularisation
https://github.com/krantirk/BERT-Pretrained-model
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/ksouvik52/DNR_ASP_DAC2021
A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs
https://github.com/kuanzi/Bayesian_quant
https://github.com/leonidasy/fast-vocabulary-transfer
https://github.com/lizeng614/SqueezeNet-Neural-Style-Pytorch
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/llx666/git_demo
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/lyronctk/quant-noisier-speech
Training with Quantization Noise for Extreme Model Compression
https://github.com/m1lhaus/SimpleSqueezeNet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/maheshkaran/Nervana-Distiller
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
https://github.com/marload/ConvNets-TensorFlow2
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/matteo-rizzo/fc4-pytorch
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/maxemerling/COVID_CT
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mcordier/Papers-Presentation-ML-Reading-Group-
Diversity Networks: Neural Network Compression Using Determinantal Point Processes
https://github.com/mdsarfarazulh/fire-module
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/microsoft/NeuralSpeech/tree/master/LightSpeech
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
https://github.com/microsoft/bitblas
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/microsoft/moonlit
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
https://github.com/milliemince/eBay-shipping-predictions
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mindlab-ai/mindcv/blob/main/mindcv/models/squeezenet.py
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mindspore-ai/models/tree/master/official/cv/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mindspore-ai/models/tree/master/research/cv/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mindspore-courses/heads-on-mindspore/blob/main/1-best-practice/models
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/squeezenet.py
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/mit-han-lab/ProxylessNAS
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
https://github.com/mit-han-lab/haq
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
https://github.com/mit-han-lab/haq-release
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
https://github.com/mit-han-lab/llm-awq
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/mit-han-lab/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.