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/ShaowuChen/WHC

공식 코드

WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks

https://github.com/Shiweiliuiiiiiii/GraNet

공식 코드

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

https://github.com/UCMerced-ML/LC-model-compression

공식 코드

A flexible, extensible software framework for model compression based on the LC algorithm

https://github.com/VITA-Group/LightGaussian

공식 코드

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

https://github.com/VITA-Group/SDCLR

공식 코드

Self-Damaging Contrastive Learning

https://github.com/VainF/Torch-Pruning

공식 코드

DepGraph: Towards Any Structural Pruning

https://github.com/aakutalev/ewc-features

공식 코드

Stabilizing Elastic Weight Consolidation method in practical ML tasks and using weight importances for neural network pruning

https://github.com/abx393/llm-pruning-calibration-data

공식 코드

Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning

https://github.com/aim-uofa/loraprune

공식 코드

LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

https://github.com/alecwangcq/EigenDamage-Pytorch

공식 코드

EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis

https://github.com/alecwangcq/GraSP

공식 코드

Picking Winning Tickets Before Training by Preserving Gradient Flow

https://github.com/allenai/dnw

공식 코드

Discovering Neural Wirings

https://github.com/amazon-science/llm-rank-pruning

공식 코드

LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models

https://github.com/ambroggi/pruning-project-for-deep-neural-networks

공식 코드

Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge

https://github.com/amzn/xfer/tree/master/nn_similarity_index

공식 코드

Similarity of Neural Networks with Gradients

https://github.com/anonymous47823493/EagleEye

공식 코드

EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

https://github.com/apurba-nsu-rnd-lab/pcnn_pruning

공식 코드

3D Point Cloud Network Pruning: When Some Weights Do not Matter

https://github.com/arunmallya/packnet

공식 코드

PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

https://github.com/astorfi/attention-guided-sparsity

공식 코드

Attention-Based Guided Structured Sparsity of Deep Neural Networks

https://github.com/athglentis/feather

공식 코드

Feather: An Elegant Solution to Effective DNN Sparsification

https://github.com/avysogorets/effective-sparsity

공식 코드

Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity

https://github.com/babajide07/Redundant-Feature-Pruning-Pytorch-Implementation

공식 코드

Building Efficient ConvNets using Redundant Feature Pruning

https://github.com/bojue-wang/ccm-lrr

공식 코드

Filter Pruning For CNN With Enhanced Linear Representation Redundancy

https://github.com/cardwing/codes-for-pvkd

공식 코드

Network Pruning via Resource Reallocation

https://github.com/casia-iva-lab/flap

공식 코드

Fluctuation-based Adaptive Structured Pruning for Large Language Models

https://github.com/casia-iva-lab/masksparsity

공식 코드

Pruning-aware Sparse Regularization for Network Pruning

https://github.com/chomd90/extreme_sparse

공식 코드

ESPN: Extremely Sparse Pruned Networks

https://github.com/chrishamblin7/circuit_explorer

공식 코드

Pruning for Feature-Preserving Circuits in CNNs

https://github.com/clevercool/TileSparsity

공식 코드

Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity

https://github.com/crispianm/st-mfnet-mini

공식 코드

ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation

https://github.com/danczs/NetworkAdjustment

공식 코드

Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio

https://github.com/deep-fry/mayo

공식 코드

Dynamic Channel Pruning: Feature Boosting and Suppression

https://github.com/derronxu/sparsebert

공식 코드

Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm

https://github.com/diaoenmao/pruning-deep-neural-networks-from-a-sparsity-perspective

공식 코드

Pruning Deep Neural Networks from a Sparsity Perspective

https://github.com/drl-casia/abcp

공식 코드

ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search

https://github.com/edac-ml4h/edac-ml4h

공식 코드

EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection

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