Awesome Open Source
Awesome Open Source


This repository includes the code used to evaluate NAS methods on 5 different datasets, as well as the code used to augment architectures with different protocols, as mentioned in our ICLR2020 paper ( Scripts exemples are provided in each folder.

ICLR2020 video poster presentation

The video from our ICLR2020 poster presentation is available at


All code used to generate the plots of the paper can be found in the "Plots" folder.

Randomly Sampled Architectures

You can find all sampled architectures and corresponding training logs in Plots\data\modified_search_space.


In the data folder, you will find the data splits for Sport-8, MIT-67 and Flowers-102 in .csv files.

You can download these datasets on the following web sites :

Sport-8 :

MIT-67 :

Flowers-102 :

The data path has to be set the following way : dataset/train/classes/images for the training set, dataset/test/classes/images for the test set.

We used the following repositories :


Paper : Liu, Hanxiao, Karen Simonyan, and Yiming Yang. "Darts: Differentiable architecture search." arXiv preprint arXiv:1806.09055 (2018).

Unofficial updated implementation :


Paper : Xin Chen, Lingxi Xie, Jun Wu, Qi Tian. "Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation." ICCV, 2019.

Official implementation :


Paper : Weng, Yu, et al. "Automatic Convolutional Neural Architecture Search for Image Classification Under Different Scenes." IEEE Access 7 (2019): 38495-38506.

Official implementation :


Paper : Guilin Li et al. "StacNAS: Towards Stable and Consistent Differentiable Neural Architecture Search." arXiv preprint arXiv:1909.11926 (2019).

Implementation : provided by the authors


Paper : Pham, Hieu, et al. "Efficient neural architecture search via parameter sharing." arXiv preprint arXiv:1802.03268 (2018).

Official Tensorflow implementation :

Unofficial Pytorch implementation :


Paper : Maria Carlucci, Fabio, et al. "MANAS: Multi-Agent Neural Architecture Search." arXiv preprint arXiv:1909.01051 (2019).

Implementation : provided by the authors.


Paper : Lu, Zhichao, et al. "NSGA-NET: a multi-objective genetic algorithm for neural architecture search." arXiv preprint arXiv:1810.03522 (2018).

Official implementation :


Paper : Luo, Renqian, et al. "Neural architecture optimization." Advances in neural information processing systems. 2018.

Official Pytorch implementation :

For the two following methods, we have not yet performed consistent experiments (therefore the methods are not included in the paper). Nonetheless, we provide runnable code that could provide relevant insights (similar to those provided in the paper on the other methods) on these methods.


Paper : Xu, Yuhui, et al. "PC-DARTS: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search." arXiv preprint arXiv:1907.05737 (2019).

Official implementation :


Paper : Laube, Kevin Alexander, and Andreas Zell. "Prune and Replace NAS." arXiv preprint arXiv:1906.07528 (2019).

Official implementation :


Paper : Cubuk, Ekin D., et al. "Autoaugment: Learning augmentation policies from data." arXiv preprint arXiv:1805.09501 (2018).

Unofficial Pytorch implementation :


If you found this work useful, consider citing us:

title={NAS evaluation is frustratingly hard},
author={Antoine Yang and Pedro M. Esperança and Fabio M. Carlucci},
booktitle={International Conference on Learning Representations},

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (47,857
benchmark (209
automl (93
evaluation (61
neural-architecture-search (49
nas (35

Find Open Source By Browsing 7,000 Topics Across 59 Categories