AutoDL Projects
1.0.0
自動化深度學習項目(Autodl-Projects)是每個人的開源,輕巧但有用的項目。該項目實施了幾種神經體系結構搜索(NAS)和高參數優化(HPO)算法。 中文介紹見readme_cn.md
誰應該考慮使用自動項目
我們為什麼要使用autodl-projects
目前,該項目提供以下算法和腳本來運行它們。請參閱“描述”列中提供的鏈接中的詳細信息。
| 類型 | abbrv | 演算法 | 描述 |
|---|---|---|---|
| nas | tas | 通過可轉換體系結構搜索進行網絡修剪 | Neurips-2019-Tas.md |
| 飛鏢 | 飛鏢:可區分架構搜索 | ICLR-2019-darts.md | |
| gdas | 在四個GPU小時內搜索強大的神經建築 | CVPR-2019-GDAS.MD | |
| 設定 | 通過自我評估的模板網絡搜索單發神經架構搜索 | ICCV-2019-setn.md | |
| NAS Bench-2011 | NAS Bench-2011:擴展可再現神經體系結構搜索的範圍 | NAS Bench-2011.md | |
| 納斯板凳 | NATS板凳:為建築拓撲和大小的基準測試NAS算法 | Nats-Bench.md | |
| ... | enas / rea / readforce / bohb | 請檢查原始論文 | NAS-Bench-201.MD Nats-Bench.md |
| HPO | HPO-CG | 高參數優化,近似梯度 | 即將推出 |
| 基本的 | 重新連接 | 基於深度學習的圖像分類 | 基線 |
首先,請使用pip install .安裝xautodl庫。
請安裝Python>=3.6和PyTorch>=1.5.0 。 (您可以使用較低版本的Python和Pytorch,但可能有錯誤)。一些可視化代碼可能需要opencv 。
Cifar和Imagenet應下載並提取到$TORCH_HOME中。一些方法使用知識蒸餾(KD),需要預訓練的模型。請從Google Drive(或自己訓練)下載這些模型,然後將其保存到.latent-data中。
請使用
git clone --recurse-submodules https://github.com/D-X-Y/AutoDL-Projects.git XAutoDL
使用子模型下載此回購。
如果您發現該項目有助於您的研究,請考慮引用相關論文:
@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}
}
如果您想為此倉庫做出貢獻,請參閱parduting.md。此外,請遵循導電守則。
我們將black用於Python代碼格式。請使用black . -l 88 。
整個代碼庫均在MIT許可下。