Papers with Code 아카이브

Network Pruning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 5
보존된 평가 기록: 34

Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.

Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

코드

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

https://github.com/ejlb/squeezenet-chainer

공식 코드

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

https://github.com/eliacunegatti/neuroal

공식 코드

Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training

https://github.com/facebookresearch/spartan

공식 코드

Spartan: Differentiable Sparsity via Regularized Transportation

https://github.com/fastmachinelearning/nac-opt

공식 코드

Neural Architecture Codesign for Fast Physics Applications

https://github.com/friendshipkim/neuron-merging

공식 코드

Neuron Merging: Compensating for Pruned Neurons

https://github.com/fxmeng/rmnet

공식 코드

RMNet: Equivalently Removing Residual Connection from Networks

https://github.com/gahaalt/reproducing-comparing-rewinding-and-finetuning

공식 코드

Reproducibility Study: Comparing Rewinding and Fine-tuning in Neural Network Pruning

https://github.com/georgeretsi/SparsityLoss

공식 코드

Weight Pruning via Adaptive Sparsity Loss

https://github.com/google-research/google-research/tree/master/pruning_identified_exemplars

공식 코드

What Do Compressed Deep Neural Networks Forget?

https://github.com/halomoto/directiontuningattack

공식 코드

Improving the Transferability of Adversarial Examples via Direction Tuning

https://github.com/haria/SqueezeNet

공식 코드

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

https://github.com/harshildarji/thesis

공식 코드

Investigating Sparsity in Recurrent Neural Networks

https://github.com/he-y/awesome-pruning

공식 코드

Structured Pruning for Deep Convolutional Neural Networks: A survey

https://github.com/hezheug/sparse-double-descent

공식 코드

Sparse Double Descent: Where Network Pruning Aggravates Overfitting

https://github.com/hrcheng1066/awesome-pruning

공식 코드

A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations

https://github.com/hsilva664/discrete_nn

공식 코드

What to Do When Your Discrete Optimization Is the Size of a Neural Network?

https://github.com/huawei-noah/Efficient-Computing

공식 코드

Towards Higher Ranks via Adversarial Weight Pruning

https://github.com/huawei-noah/Pruning

공식 코드

SCOP: Scientific Control for Reliable Neural Network Pruning

https://github.com/huggingface/transformers/tree/master/examples/movement-pruning

공식 코드

Movement Pruning: Adaptive Sparsity by Fine-Tuning

https://github.com/idt-iti/lightweight-face-detector-pruning

공식 코드

Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion

https://github.com/inspire-group/compactness-robustness

공식 코드

HYDRA: Pruning Adversarially Robust Neural Networks

https://github.com/itsmattei/ken

공식 코드

Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models

https://github.com/iurada/px-ntk-pruning

공식 코드

Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning

https://github.com/j201/gibbs-pruning

공식 코드

A Framework for Neural Network Pruning Using Gibbs Distributions

https://github.com/jaeho-lee/layer-adaptive-sparsity

공식 코드

Layer-adaptive sparsity for the Magnitude-based Pruning

https://github.com/jayroxis/dam-pytorch

공식 코드

Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)

https://github.com/jerry-chee/modelpreservecompressionnn

공식 코드

Model Preserving Compression for Neural Networks

https://github.com/jiamian-wang/iterative-soft-shrinkage-sr

공식 코드

Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution

https://github.com/jjgo/shrinkbench

공식 코드

What is the State of Neural Network Pruning?

https://github.com/johnrachwan123/Early-Cropression-via-Gradient-Flow-Preservation

공식 코드

Winning the Lottery Ahead of Time: Efficient Early Network Pruning

https://github.com/jshilong/FisherPruning

공식 코드

Group Fisher Pruning for Practical Network Compression

https://github.com/junjieliu2910/DynamicSaprseTraining

공식 코드

Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers

https://github.com/justincosentino/robust-sparse-networks

공식 코드

The Search for Sparse, Robust Neural Networks

https://github.com/kangxiatao/prune_tf2_master

공식 코드

A pruning method based on the dissimilarity of angle among channels and filters

https://github.com/kangxiatao/rlpanning

공식 코드

Neural Network Panning: Screening the Optimal Sparse Network Before Training

https://github.com/landskape-ai/progressive-pruning

공식 코드

APP: Anytime Progressive Pruning

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