.. | ||
bohb.py | ||
random_wo_share.py | ||
README.md | ||
regularized_ea.py | ||
reinforce.py | ||
run-all.sh | ||
search-cell.py | ||
search-size.py |
NAS Algorithms evaluated in NATS-Bench
The Python files in this folder are used to re-produce the results in ``NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size''.
search-size.py
contains codes for weight-sharing-based search on the size search space.search-cell.py
contains codes for weight-sharing-based search on the topology search space.bohb.py
contains the BOHB algorithm for both size and topology search spaces.random_wo_share.py
contains the random search algorithm for both search spaces.regularized_ea.py
contains the REA algorithm for both search spaces.reinforce.py
contains the REINFORCE algorithm for both search spaces.
Requirements
nats_bench
>=v1.2 : you can usepip install nats_bench
to install or from sourceshpbandster
: if you want to run BOHB
Citation
If you find that this project helps your research, please consider citing the related paper:
@article{dong2021nats,
title = {{NATS-Bench}: Benchmarking NAS Algorithms for Architecture Topology and Size},
author = {Dong, Xuanyi and Liu, Lu and Musial, Katarzyna and Gabrys, Bogdan},
doi = {10.1109/TPAMI.2021.3054824},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
year = {2021},
note = {\mbox{doi}:\url{10.1109/TPAMI.2021.3054824}}
}