Papers with Code 아카이브
Dynamic neural networks
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Dynamic neural networks are adaptable models that can change their structure or parameters during training or inference based on input complexity or computational constraints. They offer benefits like improved efficiency, adaptability, and scalability compared to static architectures.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/UoS-EEC/DynamicOFA
공식 코드Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices
https://github.com/aaltoml/calibrated-dnn
공식 코드https://github.com/ajaysub110/satbench
공식 코드https://github.com/anonymous2015258/Early_Attack
공식 코드https://github.com/baithebest/drain
공식 코드Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks
https://github.com/halimabouzidi/hadas
공식 코드HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling
https://github.com/lakehanne/FARNN
공식 코드Nonlinear Systems Identification Using Deep Dynamic Neural Networks
https://github.com/networkslab/dynn
공식 코드Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN
https://github.com/shaojiawei07/VL-VFE
공식 코드Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
https://github.com/yangle15/DyFADet-pytorch
공식 코드DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
https://github.com/DTU-PAS/awesome-dynn-for-cv
A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion
https://github.com/facebookresearch/fairscale
AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.