https://github.com/Mind23-2/MindCode-5/tree/main/proxylessnas
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
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.
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
GraphPAS: Parallel Architecture Search for Graph Neural Networks
GraphPAS: Parallel Architecture Search for Graph Neural Networks
DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Learning Transferable Architectures for Scalable Image Recognition
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
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
NAS-FCOS: Fast Neural Architecture Search for Object Detection
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Robust and Accurate Object Detection via Adversarial Learning
Nystrom Method for Accurate and Scalable Implicit Differentiation
Robust and Accurate Object Detection via Adversarial Learning
Nystrom Method for Accurate and Scalable Implicit Differentiation
Smell and Emotion: Recognising emotions in smell-related artworks
GraphPAS: Parallel Architecture Search for Graph Neural Networks
Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
SAFE ML: Surrogate Assisted Feature Extraction for Model Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.