From 08d21781eb574ac2ac54237a4a8eeee9043b9f7c Mon Sep 17 00:00:00 2001 From: Jack Turner Date: Tue, 9 Jun 2020 10:04:59 +0100 Subject: [PATCH 1/3] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 1826655..669cb9f 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ -# Neural Architecture Search Without Training +# [Neural Architecture Search Without Training](https://arxiv.org/abs/2006.04647) -This repository contains code for replicating our paper on NAS without training. +This repository contains code for replicating our paper, [NAS Without Training](https://arxiv.org/abs/2006.04647). ## Setup From 8167081b8510b34cefe22ee5d43b34b83bbeb8dc Mon Sep 17 00:00:00 2001 From: Jack Turner Date: Tue, 9 Jun 2020 10:08:15 +0100 Subject: [PATCH 2/3] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 669cb9f..57d3e69 100644 --- a/README.md +++ b/README.md @@ -35,7 +35,7 @@ Each command will finish by calling `process_results.py`, which will print a tab | Ours (N=100) | 17.4139 | 88.45 +- 1.46 | 91.61 +- 1.71 | 66.42 +- 3.27 | 66.56 +- 3.28 | 36.56 +- 6.70 | 36.37 +- 6.97 -To try different sample sizes, simply change the `--n_samples` argument in the call to `search.py`, and update the list of sample sizes on line 51 of `process_results.py`. +To try different sample sizes, simply change the `--n_samples` argument in the call to `search.py`, and update the list of sample sizes [this line](https://github.com/BayesWatch/nas-without-training/blob/master/process_results.py#L51) of `process_results.py`. Note that search times may vary from the reported result owing to hardware setup. From 76d23b14acc83e0fb9fabfaff0a8aff50fa40868 Mon Sep 17 00:00:00 2001 From: Jack Turner Date: Tue, 9 Jun 2020 10:09:40 +0100 Subject: [PATCH 3/3] Update README.md --- README.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/README.md b/README.md index 57d3e69..d25a01a 100644 --- a/README.md +++ b/README.md @@ -44,3 +44,18 @@ The code is licensed under the MIT licence. ## Acknowledgements This repository makes liberal use of code from the [AutoDL](https://github.com/D-X-Y/AutoDL-Projects) library. We also rely on [NAS-Bench-201](https://github.com/D-X-Y/NAS-Bench-201). + +## Citing us + +If you use or build on our work, please consider citing us: + +``` +@misc{mellor2020neural, + title={Neural Architecture Search without Training}, + author={Joseph Mellor and Jack Turner and Amos Storkey and Elliot J. Crowley}, + year={2020}, + eprint={2006.04647}, + archivePrefix={arXiv}, + primaryClass={cs.LG} +} +```