https://github.com/MS-Mind/MS-Code-08/tree/main/nas-fpn
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Automated Machine Learning (AutoML) is a general concept which covers diverse techniques for automated model learning including automatic data preprocessing, architecture search, and model selection. Source: Evaluating recommender systems for AI-driven data science (1905.09205)
Source: CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Learning Transferable Architectures for Scalable Image Recognition
Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deployment
Optimizing Millions of Hyperparameters by Implicit Differentiation
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
ISyNet: Convolutional Neural Networks design for AI accelerator
MnasNet: Platform-Aware Neural Architecture Search for Mobile
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
ISyNet: Convolutional Neural Networks design for AI accelerator
MnasNet: Platform-Aware Neural Architecture Search for Mobile
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
MnasNet: Platform-Aware Neural Architecture Search for Mobile
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.