{"id":13784052,"url":"https://github.com/thuml/TransNorm","last_synced_at":"2025-05-11T19:32:31.328Z","repository":{"id":105072520,"uuid":"223171740","full_name":"thuml/TransNorm","owner":"thuml","description":"Code release for \"Transferable Normalization: Towards Improving Transferability of Deep Neural Networks\" (NeurIPS 2019)","archived":false,"fork":false,"pushed_at":"2020-12-10T07:39:28.000Z","size":56346,"stargazers_count":79,"open_issues_count":0,"forks_count":13,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-11-17T20:48:10.843Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/thuml.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-11-21T12:42:50.000Z","updated_at":"2024-10-31T10:34:05.000Z","dependencies_parsed_at":"2024-01-07T02:43:25.438Z","dependency_job_id":"e3a9fcdd-be1d-4a17-8752-64da01fbfd26","html_url":"https://github.com/thuml/TransNorm","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/thuml%2FTransNorm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuml%2FTransNorm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuml%2FTransNorm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thuml%2FTransNorm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thuml","download_url":"https://codeload.github.com/thuml/TransNorm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253621244,"owners_count":21937495,"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":[],"created_at":"2024-08-03T19:00:34.874Z","updated_at":"2025-05-11T19:32:27.171Z","avatar_url":"https://github.com/thuml.png","language":"Python","readme":"# TransNorm\nCode release for [\"Transferable Normalization: Towards Improving Transferability of Deep Neural Networks\"](https://papers.nips.cc/paper/8470-transferable-normalization-towards-improving-transferability-of-deep-neural-networks) (NeurIPS 2019)\n\n## Prerequisites\n- PyTorch \u003e= 0.4.0 (with suitable CUDA and CuDNN version)\n- torchvision \u003e= 0.2.1\n- Python3\n- Numpy\n- argparse\n- PIL\n\n## Training\n```\nOffice-31\n\npythonn train_image.py --gpu_id id --net ResNet50 --dset office --test_interval 500 --s_dset_path ../data/office/amazon_list.txt --t_dset_path ../data/office/webcam_list.txt\n```\n```\nOffice-Home\n\npythonn train_image.py --gpu_id id --net ResNet50 --dset office-home --test_interval 2000 --s_dset_path ../data/office-home/Art.txt --t_dset_path ../data/office-home/Clipart.txt\n```\n```\nVisDA 2017\n\npythonn train_image.py --gpu_id id --net ResNet50 --dset visda --test_interval 5000 --s_dset_path ../data/visda-2017/train_list.txt --t_dset_path ../data/visda-2017/validation_list.txt\n```\n```\nImage-clef\n\npythonn train_image.py --gpu_id id --net ResNet50 --dset image-clef --test_interval 500 --s_dset_path ../data/image-clef/b_list.txt --t_dset_path ../data/image-clef/i_list.txt\n```\n\n## Acknowledgement\nThis code is implemented based on the published code of CDAN and BatchNorm, and it is our pleasure to acknowledge their contributions.\nCDAN (Conditional Adversarial Domain Adaptation)\nBatchNorm (Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift)\n\n## Citation\nIf you use this code for your research, please consider citing:\n```\n@inproceedings{Wang19TransNorm,\n    title = {Transferable Normalization: Towards Improving Transferability of Deep Neural Networks},\n    author = {Wang, Ximei and Jin, Ying and Long, Mingsheng and Wang, Jianmin and Jordan, Michael I},\n    booktitle = {Advances in Neural Information Processing Systems 32},\n    year = {2019}\n}\n```\n\n## Contact\nIf you have any problem about our code, feel free to contact\n- wxm17@mails.tsinghua.edu.cn\n- longmingsheng@gmail.com\n\nor describe your problem in Issues.\n","funding_links":[],"categories":["2019"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthuml%2FTransNorm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthuml%2FTransNorm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthuml%2FTransNorm/lists"}