HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Neural Architecture Search On Nats Bench 2

Metrics

Test Accuracy

Results

Performance results of various models on this benchmark

Model Name
Test Accuracy
Paper TitleRepository
LayerNAS73.01±0.63LayerNAS: Neural Architecture Search in Polynomial Complexity-
TE-NAS (Chen et al., 2021)71.24Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
NASI (Shu et al., 2021)71.20NASI: Label- and Data-agnostic Neural Architecture Search at Initialization-
GreenMachine-1-GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS
GreenMachine-3-GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS
EigenNas (Zhu et al., 2022)71.42Generalization Properties of NAS under Activation and Skip Connection Search-
PPO (Schulman et al., 2017)71.68Proximal Policy Optimization Algorithms
RE (Real et al., 2019)71.40Regularized Evolution for Image Classifier Architecture Search
GreenMachine-2-GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS
KNAS (Xu et al., 2021)68.91KNAS: Green Neural Architecture Search
FairNAS (Chu et al., 2021)71.00FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
0 of 11 row(s) selected.