{"id":22919900,"url":"https://github.com/zjcv/networkslimming","last_synced_at":"2025-05-12T20:20:34.227Z","repository":{"id":54482235,"uuid":"387506555","full_name":"ZJCV/NetworkSlimming","owner":"ZJCV","description":" [ICCV 2017] Learning Efficient Convolutional Networks through Network Slimming","archived":false,"fork":false,"pushed_at":"2021-10-09T14:37:08.000Z","size":60,"stargazers_count":6,"open_issues_count":2,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-05-12T20:20:12.294Z","etag":null,"topics":["channel-pruning","mobilenet","network-pruning","network-slimming","pytorch","resnet","vggnet","zcls"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ZJCV.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":"2021-07-19T15:12:39.000Z","updated_at":"2023-03-08T07:56:05.000Z","dependencies_parsed_at":"2022-08-13T17:20:25.719Z","dependency_job_id":null,"html_url":"https://github.com/ZJCV/NetworkSlimming","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJCV%2FNetworkSlimming","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJCV%2FNetworkSlimming/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJCV%2FNetworkSlimming/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZJCV%2FNetworkSlimming/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZJCV","download_url":"https://codeload.github.com/ZJCV/NetworkSlimming/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253815079,"owners_count":21968566,"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":["channel-pruning","mobilenet","network-pruning","network-slimming","pytorch","resnet","vggnet","zcls"],"created_at":"2024-12-14T07:13:49.435Z","updated_at":"2025-05-12T20:20:34.178Z","avatar_url":"https://github.com/ZJCV.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"right\"\u003e\n  Language:\n    🇺🇸\n  \u003ca title=\"Chinese\" href=\"./README.zh-CN.md\"\u003e🇨🇳\u003c/a\u003e\n\u003c/div\u003e\n\n \u003cdiv align=\"center\"\u003e\u003ca title=\"\" href=\"https://github.com/ZJCV/NetworkSlimming\"\u003e\u003cimg align=\"center\" src=\"./imgs/NetworkSlimming.png\"\u003e\u003c/a\u003e\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  «NetworkSlimming» re-implements the paper \u003ca title=\"\" href=\"https://arxiv.org/abs/1708.06519\"\u003eLearning Efficient Convolutional Networks through Network Slimming\u003c/a\u003e\n\u003cbr\u003e\n\u003cbr\u003e\n  \u003ca href=\"https://github.com/RichardLitt/standard-readme\"\u003e\u003cimg src=\"https://img.shields.io/badge/standard--readme-OK-green.svg?style=flat-square\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://conventionalcommits.org\"\u003e\u003cimg src=\"https://img.shields.io/badge/Conventional%20Commits-1.0.0-yellow.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"http://commitizen.github.io/cz-cli/\"\u003e\u003cimg src=\"https://img.shields.io/badge/commitizen-friendly-brightgreen.svg\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nMore training statistics can see:\n\n* [Details](./docs/details.md)\n\n## Table of Contents\n\n- [Table of Contents](#table-of-contents)\n- [Background](#background)\n- [Usage](#usage)\n- [Maintainers](#maintainers)\n- [Thanks](#thanks)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Background\n\n`Network Slimming` uses `L1` regularization to sparsely train the BN layer's `scaling factor`; After the training, it performs channel-level pruning operation; Finally, by fine-tuning to recovery performance. it achieves good results in practical application.\n\n## Usage\n\nFirst, you need set env for `PYTHONPATH` and `CUDA_VISIBLE_DEVICES`\n\n```angular2html\n$ export PYTHONPATH=\u003cproject root path\u003e\n$ export CUDA_VISIBLE_DEVICES=0\n```\n\nThen, begin `train-prune-finetuning`\n\n* For train\n\n```\n$ python tools/train.py -cfg=configs/vggnet/vgg16_bn_cifar100_224_e100_sgd_mslr_slim_1e_4.yaml\n```\n\n* For prune\n\n```angular2html\n$ python tools/prune/prune_vggnet.py\n```\n\n* For fine-tuning\n\n```angular2html\n$ python tools/train.py -cfg=configs/vggnet/refine_pruned_0_2_vgg16_bn_cifar100_224_e100_sgd_mslr_slim_1e_4.yaml\n```\n\nFinally, set the fine-tuning model path in the `PRELOADED` option of the configuration file\n\n```angular2html\n$ python tools/test.py -cfg=configs/vggnet/refine_pruned_0_2_vgg16_bn_cifar100_224_e100_sgd_mslr_slim_1e_4.yaml\n```\n\n## Maintainers\n\n* zhujian - *Initial work* - [zjykzj](https://github.com/zjykzj)\n\n## Thanks\n\n* [ Eric-mingjie/network-slimming ](https://github.com/Eric-mingjie/network-slimming)\n* [ wlguan/MobileNet-v2-pruning ](https://github.com/wlguan/MobileNet-v2-pruning)\n* [ 666DZY666/micronet](https://github.com/666DZY666/micronet)\n* [ foolwood/pytorch-slimming ](https://github.com/foolwood/pytorch-slimming)\n\n```\n@misc{liu2017learning,\n      title={Learning Efficient Convolutional Networks through Network Slimming}, \n      author={Zhuang Liu and Jianguo Li and Zhiqiang Shen and Gao Huang and Shoumeng Yan and Changshui Zhang},\n      year={2017},\n      eprint={1708.06519},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n## Contributing\n\nAnyone's participation is welcome! Open an [issue](https://github.com/ZJCV/NetworkSlimming/issues) or submit PRs.\n\nSmall note:\n\n* Git submission specifications should be complied\n  with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0-beta.4/)\n* If versioned, please conform to the [Semantic Versioning 2.0.0](https://semver.org) specification\n* If editing the README, please conform to the [standard-readme](https://github.com/RichardLitt/standard-readme)\n  specification.\n\n## License\n\n[Apache License 2.0](LICENSE) © 2021 zjykzj","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzjcv%2Fnetworkslimming","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzjcv%2Fnetworkslimming","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzjcv%2Fnetworkslimming/lists"}