{"id":22493216,"url":"https://github.com/negrinho/deep_architect_legacy","last_synced_at":"2025-07-19T14:32:54.949Z","repository":{"id":84482789,"uuid":"89671119","full_name":"negrinho/deep_architect_legacy","owner":"negrinho","description":"DeepArchitect: Automatically Designing and Training Deep Architectures","archived":false,"fork":false,"pushed_at":"2019-10-01T04:08:23.000Z","size":35,"stargazers_count":145,"open_issues_count":1,"forks_count":20,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-04-09T01:41:23.671Z","etag":null,"topics":["architecture-search","auto-ml","automatic-machine-learning","deep-learning","hyperparameter-optimization","machine-learning","neural-architecture-search"],"latest_commit_sha":null,"homepage":null,"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/negrinho.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-04-28T05:35:51.000Z","updated_at":"2025-03-24T09:41:49.000Z","dependencies_parsed_at":"2023-03-12T23:08:38.409Z","dependency_job_id":null,"html_url":"https://github.com/negrinho/deep_architect_legacy","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/negrinho/deep_architect_legacy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/negrinho%2Fdeep_architect_legacy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/negrinho%2Fdeep_architect_legacy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/negrinho%2Fdeep_architect_legacy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/negrinho%2Fdeep_architect_legacy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/negrinho","download_url":"https://codeload.github.com/negrinho/deep_architect_legacy/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/negrinho%2Fdeep_architect_legacy/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265947490,"owners_count":23853382,"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":["architecture-search","auto-ml","automatic-machine-learning","deep-learning","hyperparameter-optimization","machine-learning","neural-architecture-search"],"created_at":"2024-12-06T18:34:33.580Z","updated_at":"2025-07-19T14:32:54.940Z","avatar_url":"https://github.com/negrinho.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DeepArchitect: Automatically Designing and Training Deep Architectures\n\n**IMPORTANT:** This repo is not under active development.\nIt contains a prototype for the ideas described in this [paper](https://arxiv.org/abs/1704.08792).\nSee our [NeurIPS 2019 paper](https://arxiv.org/abs/1909.13404) for the latest developments.\nThe code and documentation for the latest framework can be found [here](https://github.com/negrinho/deep_architect).\n\nThis repository contains a Python implementation of the DeepArchitect framework described in\n[our paper](https://arxiv.org/abs/1704.08792).\nTo get familiar with the framework, we recommend starting with\n[this tutorial](https://github.com/negrinho/deep_architect_legacy/blob/master/tutorial.ipynb).\n\nA tar file with the logs of the experiments in the paper is available [here](http://www.cs.cmu.edu/~negrinho/assets/papers/deep_architect/logs.tar.gz). You can download it, unzip it in the top folder of the repo, and generate the plots of the paper using `plots.py`. The logs are composed of text and pickle files. It may be informative to inspect them. The experiments reported in the paper can be reproduced using `experiments.py`.\n\nContributors:\n[Renato Negrinho](http://www.cs.cmu.edu/~negrinho/),\n[Geoff Gordon](http://www.cs.cmu.edu/~ggordon/),\n[Matt Gormley](http://www.cs.cmu.edu/~mgormley/),\n[Christoph Dann](http://cdann.net/),\n[Matt Barnes](http://www.cs.cmu.edu/~mbarnes1/).\n\n\n## References\n\n```\n@article{negrinho2017deeparchitect,\n  title={Deeparchitect: Automatically designing and training deep architectures},\n  author={Negrinho, Renato and Gordon, Geoff},\n  journal={arXiv preprint arXiv:1704.08792},\n  year={2017}\n}\n\n@article{negrinho2019towards,\n  title={Towards modular and programmable architecture search},\n  author={Negrinho, Renato and Patil, Darshan and Le, Nghia and Ferreira, Daniel and Gormley, Matthew and Gordon, Geoffrey},\n  journal={Neural Information Processing Systems},\n  year={2019}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnegrinho%2Fdeep_architect_legacy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnegrinho%2Fdeep_architect_legacy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnegrinho%2Fdeep_architect_legacy/lists"}