{"id":15640181,"url":"https://github.com/bzantium/pytorch-admm-pruning","last_synced_at":"2026-03-02T00:31:31.999Z","repository":{"id":64232023,"uuid":"203540935","full_name":"bzantium/pytorch-admm-pruning","owner":"bzantium","description":"Prune DNN using Alternating Direction Method of Multipliers (ADMM)","archived":false,"fork":false,"pushed_at":"2019-10-15T03:35:26.000Z","size":16,"stargazers_count":100,"open_issues_count":2,"forks_count":18,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-30T07:35:58.349Z","etag":null,"topics":["admm","deep-neural-networks","pruning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bzantium.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}},"created_at":"2019-08-21T08:29:59.000Z","updated_at":"2025-02-19T09:12:24.000Z","dependencies_parsed_at":"2023-01-15T05:45:54.691Z","dependency_job_id":null,"html_url":"https://github.com/bzantium/pytorch-admm-pruning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bzantium/pytorch-admm-pruning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bzantium%2Fpytorch-admm-pruning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bzantium%2Fpytorch-admm-pruning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bzantium%2Fpytorch-admm-pruning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bzantium%2Fpytorch-admm-pruning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bzantium","download_url":"https://codeload.github.com/bzantium/pytorch-admm-pruning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bzantium%2Fpytorch-admm-pruning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29988040,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T22:42:38.399Z","status":"ssl_error","status_checked_at":"2026-03-01T22:41:51.863Z","response_time":124,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["admm","deep-neural-networks","pruning"],"created_at":"2024-10-03T11:31:58.424Z","updated_at":"2026-03-02T00:31:31.952Z","avatar_url":"https://github.com/bzantium.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pytorch-admm-prunning\nIt is a pytorch implementation of DNN weight prunning with ADMM described in [**A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers**](https://arxiv.org/abs/1804.03294).\n\n## _Train and test_\n- You can simply run code by\n```\n$ python main.py\n```\n\n- In the paper, authors use **l2-norm regularization** so you can easily add by\n```\n$ python main.py --l2\n```\n\n- Beyond this paper, if you don't want to use _predefined prunning ratio_, admm with **l1 norm regularization** can give a great solution and can be simply tested by\n```\n$ python main.py --l1\n```\n\n- There are two dataset you can test in this code: **[mnist, cifar10]**. Default setting is mnist, you can change dataset by\n```\n$ python main.py --dataset cifar10\n```\n\n## _Models_\n- In this code, there are two models: **[LeNet, AlexNet]**. I use LeNet for mnist, AlexNet for cifar10 by default.\n\n## _Optimizer_\n- To prevent prunned weights from updated by optimizer, I modified Adam (named PruneAdam).\n\n## _References_\nFor this repository, I refer to _[KaiqiZhang's tensorflow implementation](https://github.com/KaiqiZhang/admm-pruning)_.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbzantium%2Fpytorch-admm-pruning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbzantium%2Fpytorch-admm-pruning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbzantium%2Fpytorch-admm-pruning/lists"}