Network Pruning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/naveen-chander/neural-network-optimization
https://github.com/oandrienko/fast-semantic-segmentation
https://github.com/ofsoundof/Heterogeneity_Hypothesis
https://github.com/optml-group/bip
https://github.com/osmr/imgclsmob
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/phiandark/SiftingFeatures
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
https://github.com/pinto0309/onnx2tf
A Quantization-Friendly Separable Convolution for MobileNets
https://github.com/prerakmody/CS4180-DL
https://github.com/pytorch/vision
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/qiaoxiao7282/seft
A Simple and Effective Pruning Approach for Large Language Models
https://github.com/rahulvigneswaran/Lottery-Ticket-Hypothesis-in-Pytorch
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
https://github.com/rcmalli/keras-squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/reallygooday/60daysofudacity
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
https://github.com/ruchikachavhan/concept-prune
A Simple and Effective Pruning Approach for Large Language Models
https://github.com/saintslab/pepr
https://github.com/sdc17/crossget
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
https://github.com/siyuan0/pytorch_model_prune
https://github.com/songhan/Deep-Compression-AlexNet
https://github.com/songhan/SqueezeNet-Deep-Compression
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/uber-research/deconstructing-lottery-tickets
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
https://github.com/unites-lab/vpns
https://github.com/vibhu444/alexnet-squeeze-mnist
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/vita-group/granet
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
https://github.com/vonclites/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/xin-w8023/SqueezeNet-PyTorch
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/xxlya/COS598D_Assignment1
https://github.com/yehuitang/Pruning
SCOP: Scientific Control for Reliable Neural Network Pruning
https://github.com/zhangtj1996/lottery-ticket-hypothesis-Mxnet
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
https://github.com/zheng-ningxin/Pruning-from-scratch
https://github.com/zjZSTU/LightWeightCNN
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://gitlab.com/birder/birder
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.