{"id":13636095,"url":"https://github.com/D-X-Y/AutoDL-Projects","last_synced_at":"2025-04-19T04:32:07.957Z","repository":{"id":41605715,"uuid":"168538768","full_name":"D-X-Y/AutoDL-Projects","owner":"D-X-Y","description":"Automated deep learning algorithms implemented in PyTorch.","archived":false,"fork":false,"pushed_at":"2022-04-24T22:18:16.000Z","size":11496,"stargazers_count":1570,"open_issues_count":15,"forks_count":283,"subscribers_count":43,"default_branch":"main","last_synced_at":"2024-11-05T03:42:18.125Z","etag":null,"topics":["autodl","automl","nas","neural-architecture-search","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/D-X-Y.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGE-LOG.md","contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":".github/CODE-OF-CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-01-31T14:30:50.000Z","updated_at":"2024-11-04T06:02:17.000Z","dependencies_parsed_at":"2022-07-05T10:00:51.849Z","dependency_job_id":null,"html_url":"https://github.com/D-X-Y/AutoDL-Projects","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/D-X-Y%2FAutoDL-Projects","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/D-X-Y%2FAutoDL-Projects/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/D-X-Y%2FAutoDL-Projects/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/D-X-Y%2FAutoDL-Projects/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/D-X-Y","download_url":"https://codeload.github.com/D-X-Y/AutoDL-Projects/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223790550,"owners_count":17203355,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["autodl","automl","nas","neural-architecture-search","pytorch"],"created_at":"2024-08-02T00:00:57.041Z","updated_at":"2024-11-09T05:31:17.733Z","avatar_url":"https://github.com/D-X-Y.png","language":"Python","funding_links":[],"categories":["\u003ca name=\"2017 Venues\"\u003e2017 Venues\u003c/a\u003e","Python","神经网络结构搜索_Neural_Architecture_Search","100 + 𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝗟𝗶𝘀𝘁 𝘄𝗶𝘁𝗵 𝗰𝗼𝗱𝗲","Uncategorized"],"sub_categories":["Uncategorized"],"readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://xuanyidong.com/resources/images/AutoDL-log.png\" width=\"400\"/\u003e\n\u003c/p\u003e\n\n---------\n[![MIT licensed](https://img.shields.io/badge/license-MIT-brightgreen.svg)](LICENSE.md)\n\nAutomated Deep Learning Projects (AutoDL-Projects) is an open source, lightweight, but useful project for everyone.\nThis project implemented several neural architecture search (NAS) and hyper-parameter optimization (HPO) algorithms.\n中文介绍见[README_CN.md](https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/README_CN.md)\n\n**Who should consider using AutoDL-Projects**\n\n- Beginners who want to **try different AutoDL algorithms**\n- Engineers who want to **try AutoDL** to investigate whether AutoDL works on your projects\n- Researchers who want to **easily** implement and experiement **new** AutoDL algorithms.\n\n**Why should we use AutoDL-Projects**\n- Simple library dependencies\n- All algorithms are in the same codebase\n- Active maintenance\n\n## AutoDL-Projects Capabilities\n\nAt 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.\n\n\u003ctable\u003e\n \u003ctbody\u003e\n    \u003ctr align=\"center\" valign=\"bottom\"\u003e\n      \u003cth\u003eType\u003c/th\u003e\n      \u003cth\u003eABBRV\u003c/th\u003e\n      \u003cth\u003eAlgorithms\u003c/th\u003e\n      \u003cth\u003eDescription\u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (1-st row) --\u003e\n    \u003ctd rowspan=\"6\" align=\"center\" valign=\"middle\" halign=\"middle\"\u003e NAS \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e TAS \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://arxiv.org/abs/1905.09717\"\u003eNetwork Pruning via Transformable Architecture Search\u003c/a\u003e \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/NeurIPS-2019-TAS.md\"\u003eNeurIPS-2019-TAS.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (2-nd row) --\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e DARTS \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://arxiv.org/abs/1806.09055\"\u003eDARTS: Differentiable Architecture Search\u003c/a\u003e \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/ICLR-2019-DARTS.md\"\u003eICLR-2019-DARTS.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (3-nd row) --\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e GDAS \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://arxiv.org/abs/1910.04465\"\u003eSearching for A Robust Neural Architecture in Four GPU Hours\u003c/a\u003e \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/CVPR-2019-GDAS.md\"\u003eCVPR-2019-GDAS.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (4-rd row) --\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e SETN \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://arxiv.org/abs/1910.05733\"\u003eOne-Shot Neural Architecture Search via Self-Evaluated Template Network\u003c/a\u003e \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/ICCV-2019-SETN.md\"\u003eICCV-2019-SETN.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (5-th row) --\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e NAS-Bench-201 \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://openreview.net/forum?id=HJxyZkBKDr\"\u003e NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search\u003c/a\u003e \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/NAS-Bench-201.md\"\u003eNAS-Bench-201.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (6-th row) --\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e NATS-Bench \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://xuanyidong.com/assets/projects/NATS-Bench\"\u003e NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size\u003c/a\u003e \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/NATS-Bench/blob/main/README.md\"\u003eNATS-Bench.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (7-th row) --\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e ... \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e ENAS / REA / REINFORCE / BOHB \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e Please check the original papers \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/NAS-Bench-201.md\"\u003eNAS-Bench-201.md\u003c/a\u003e  \u003ca href=\"https://github.com/D-X-Y/NATS-Bench/blob/main/README.md\"\u003eNATS-Bench.md\u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (start second block) --\u003e\n    \u003ctd rowspan=\"1\" align=\"center\" valign=\"middle\" halign=\"middle\"\u003e HPO \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e HPO-CG \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e Hyperparameter optimization with approximate gradient \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e coming soon \u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e \u003c!-- (start third block) --\u003e\n    \u003ctd rowspan=\"1\" align=\"center\" valign=\"middle\" halign=\"middle\"\u003e Basic \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e ResNet \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e Deep Learning-based Image Classification \u003c/td\u003e\n    \u003ctd align=\"center\" valign=\"middle\"\u003e \u003ca href=\"https://github.com/D-X-Y/AutoDL-Projects/tree/main/docs/BASELINE.md\"\u003eBASELINE.md\u003c/a\u003e \u003c/a\u003e \u003c/td\u003e\n    \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\n\n\n## Requirements and Preparation\n\n\n**First of all**, please use `pip install .` to install `xautodl` library.\n\nPlease install `Python\u003e=3.6` and `PyTorch\u003e=1.5.0`. (You could use lower versions of Python and PyTorch, but may have bugs).\nSome visualization codes may require `opencv`.\n\nCIFAR and ImageNet should be downloaded and extracted into `$TORCH_HOME`.\nSome methods use knowledge distillation (KD), which require pre-trained models. Please download these models from [Google Drive](https://drive.google.com/open?id=1ANmiYEGX-IQZTfH8w0aSpj-Wypg-0DR-) (or train by yourself) and save into `.latent-data`.\n\nPlease use\n```\ngit clone --recurse-submodules https://github.com/D-X-Y/AutoDL-Projects.git XAutoDL\n```\nto download this repo with submodules.\n\n## Citation\n\nIf you find that this project helps your research, please consider citing the related paper:\n```\n@inproceedings{dong2021autohas,\n  title     = {{AutoHAS}: Efficient Hyperparameter and Architecture Search},\n  author    = {Dong, Xuanyi and Tan, Mingxing and Yu, Adams Wei and Peng, Daiyi and Gabrys, Bogdan and Le, Quoc V},\n  booktitle = {2nd Workshop on Neural Architecture Search at International Conference on Learning Representations (ICLR)},\n  year      = {2021}\n}\n@article{dong2021nats,\n  title   = {{NATS-Bench}: Benchmarking NAS Algorithms for Architecture Topology and Size},\n  author  = {Dong, Xuanyi and Liu, Lu and Musial, Katarzyna and Gabrys, Bogdan},\n  doi     = {10.1109/TPAMI.2021.3054824},\n  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},\n  year    = {2021},\n  note    = {\\mbox{doi}:\\url{10.1109/TPAMI.2021.3054824}}\n}\n@inproceedings{dong2020nasbench201,\n  title     = {{NAS-Bench-201}: Extending the Scope of Reproducible Neural Architecture Search},\n  author    = {Dong, Xuanyi and Yang, Yi},\n  booktitle = {International Conference on Learning Representations (ICLR)},\n  url       = {https://openreview.net/forum?id=HJxyZkBKDr},\n  year      = {2020}\n}\n@inproceedings{dong2019tas,\n  title     = {Network Pruning via Transformable Architecture Search},\n  author    = {Dong, Xuanyi and Yang, Yi},\n  booktitle = {Neural Information Processing Systems (NeurIPS)},\n  pages     = {760--771},\n  year      = {2019}\n}\n@inproceedings{dong2019one,\n  title     = {One-Shot Neural Architecture Search via Self-Evaluated Template Network},\n  author    = {Dong, Xuanyi and Yang, Yi},\n  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},\n  pages     = {3681--3690},\n  year      = {2019}\n}\n@inproceedings{dong2019search,\n  title     = {Searching for A Robust Neural Architecture in Four GPU Hours},\n  author    = {Dong, Xuanyi and Yang, Yi},\n  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n  pages     = {1761--1770},\n  year      = {2019}\n}\n```\n\n# Others\n\nIf you want to contribute to this repo, please see [CONTRIBUTING.md](.github/CONTRIBUTING.md).\nBesides, please follow [CODE-OF-CONDUCT.md](.github/CODE-OF-CONDUCT.md).\n\nWe use [`black`](https://github.com/psf/black) for Python code formatter.\nPlease use `black . -l 88`.\n\n# License\nThe entire codebase is under the [MIT license](LICENSE.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FD-X-Y%2FAutoDL-Projects","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FD-X-Y%2FAutoDL-Projects","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FD-X-Y%2FAutoDL-Projects/lists"}