Automated Deep Learning Projects (AutoDL-Projects) is an open source, lightweight, but useful project for everyone. This project implemented several neural architecture search (NAS) and hyper-parameter optimization (HPO) algorithms. 中文介绍见README_CN.md

Who should consider using AutoDL-Projects

• Beginners who want to try different AutoDL algorithms
• Engineers who want to try AutoDL to investigate whether AutoDL works on your projects
• Researchers who want to easily implement and experiement new AutoDL algorithms.

Why should we use AutoDL-Projects

• Simple library dependencies
• All algorithms are in the same codebase
• Active maintenance

AutoDL-Projects Capabilities

At this moment, this project provides the following algorithms and scripts to run them. Please see the details in the link provided in the description column.

Requirements and Preparation

First of all, please use python setup.py install to install xautodl library.

Please install Python>=3.6 and PyTorch>=1.5.0. (You could use lower versions of Python and PyTorch, but may have bugs). Some visualization codes may require opencv.

CIFAR and ImageNet should be downloaded and extracted into $TORCH_HOME. Some methods use knowledge distillation (KD), which require pre-trained models. Please download these models from Google Drive (or train by yourself) and save into .latent-data.

Please use

git clone --recurse-submodules git@github.com:D-X-Y/AutoDL-Projects.git XAutoDL
git clone --recurse-submodules https://github.com/D-X-Y/AutoDL-Projects.git XAutoDL

to download this repo with submodules.

Citation

If you find that this project helps your research, please consider citing the related paper:

@inproceedings{dong2021autohas,
  title     = {{AutoHAS}: Efficient Hyperparameter and Architecture Search},
  author    = {Dong, Xuanyi and Tan, Mingxing and Yu, Adams Wei and Peng, Daiyi and Gabrys, Bogdan and Le, Quoc V},
  booktitle = {2nd Workshop on Neural Architecture Search at International Conference on Learning Representations (ICLR)},
  year      = {2021}
}
@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}}
}
@inproceedings{dong2020nasbench201,
  title     = {{NAS-Bench-201}: Extending the Scope of Reproducible Neural Architecture Search},
  author    = {Dong, Xuanyi and Yang, Yi},
  booktitle = {International Conference on Learning Representations (ICLR)},
  url       = {https://openreview.net/forum?id=HJxyZkBKDr},
  year      = {2020}
}
@inproceedings{dong2019tas,
  title     = {Network Pruning via Transformable Architecture Search},
  author    = {Dong, Xuanyi and Yang, Yi},
  booktitle = {Neural Information Processing Systems (NeurIPS)},
  pages     = {760--771},
  year      = {2019}
}
@inproceedings{dong2019one,
  title     = {One-Shot Neural Architecture Search via Self-Evaluated Template Network},
  author    = {Dong, Xuanyi and Yang, Yi},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  pages     = {3681--3690},
  year      = {2019}
}
@inproceedings{dong2019search,
  title     = {Searching for A Robust Neural Architecture in Four GPU Hours},
  author    = {Dong, Xuanyi and Yang, Yi},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages     = {1761--1770},
  year      = {2019}
}

Others

If you want to contribute to this repo, please see CONTRIBUTING.md. Besides, please follow CODE-OF-CONDUCT.md.

We use black for Python code formatter. Please use black . -l 88.

License

The entire codebase is under the MIT license.