HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Neural Architecture Search On Nats Bench 1

Métriques

Test Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Test Accuracy
Paper TitleRepository
KNAS (Xu et al., 2021)93.05KNAS: Green Neural Architecture Search
GreenMachine-2-GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS
NASI (Shu et al., 2021)93.55NASI: Label- and Data-agnostic Neural Architecture Search at Initialization-
FairNAS (Chu et al., 2021)93.23FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
GreenMachine-3-GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS
PPO (Schulman et al., 2017)94.02Proximal Policy Optimization Algorithms
LayerNAS94.34±0.12LayerNAS: Neural Architecture Search in Polynomial Complexity-
EigenNas (Zhu et al., 2022)93.46Generalization Properties of NAS under Activation and Skip Connection Search-
RE (Real et al., 2019)94.13Regularized Evolution for Image Classifier Architecture Search
TE-NAS (Chen et al., 2021)93.90Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
GreenMachine-1-GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS
0 of 11 row(s) selected.