NAS-Bench-201 is a benchmark (and search space) for neural architecture search. Each architecture consists of a predefined skeleton with a stack of the searched cell. In this way, architecture search is transformed into the problem of searching a good cell.
Source: NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
Variants: NAS-Bench-201, ImageNet-16-120, NAS-Bench-201, NAS-Bench-201, CIFAR-10, NAS-Bench-201, CIFAR-100
This dataset is used in 1 benchmark:
No recent benchmark submissions available for this dataset.
No papers with results on this dataset found.