https://github.com/kamsyn95/CL_DNN
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Quantisation and Pruning for Neural Network Compression and Regularisation
Efficient Structured Pruning and Architecture Searching for Group Convolution
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SNIP: Single-shot Network Pruning based on Connection Sensitivity
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SCOP: Scientific Control for Reliable Neural Network Pruning
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
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.