{"id":18276234,"url":"https://github.com/hilab-git/upl-sfda","last_synced_at":"2025-04-05T03:31:24.440Z","repository":{"id":184399863,"uuid":"670529358","full_name":"HiLab-git/UPL-SFDA","owner":"HiLab-git","description":null,"archived":false,"fork":false,"pushed_at":"2024-11-27T12:07:17.000Z","size":181,"stargazers_count":26,"open_issues_count":3,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-20T21:38:55.007Z","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/HiLab-git.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-25T08:56:44.000Z","updated_at":"2025-03-14T12:43:29.000Z","dependencies_parsed_at":"2024-03-06T06:38:05.988Z","dependency_job_id":"3cd0a58c-8617-4457-bae9-4a334cf602f6","html_url":"https://github.com/HiLab-git/UPL-SFDA","commit_stats":null,"previous_names":["hilab-git/upl-sfda"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FUPL-SFDA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FUPL-SFDA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FUPL-SFDA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FUPL-SFDA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HiLab-git","download_url":"https://codeload.github.com/HiLab-git/UPL-SFDA/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247284911,"owners_count":20913691,"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":"2024-11-05T12:15:29.193Z","updated_at":"2025-04-05T03:31:19.427Z","avatar_url":"https://github.com/HiLab-git.png","language":"Python","readme":"## UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation\n\nThis repository provides the code for \"UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation\".\n\n## Requirements\nNon-exhaustive list:\n* python3.6+\n* Pytorch 1.8.1\n* nibabel\n* Scipy\n* NumPy\n* Scikit-image\n* yaml\n* tqdm\n* pandas\n* scikit-image\n* SimpleITK\n\n## Usage\n1. Download the [Source model on M\u0026MS, FB, and FeTA](https://drive.google.com/drive/folders/1WF0kwDBC_xchTG-oEWpbSQjKdHZdw80s?usp=drive_link) and move the extracted source model folder to the \"save_model/source_model\" directory in your project.\nIf you prefer, you can also train the source model yourself. To do this, navigate to the config directory and open the config\\trainXX.cfg file. In the config file, locate the line that specifies train_target and change its value to False. \nFor instance, you can train the source model using modality A on the M\u0026MS datasets:\n ```\npython train_source.py --config \"./config/train2d_source.cfg\"\n```\n2. Download the [M\u0026MS Dataset](http://www.ub.edu/mnms), [FeTA Dataset](https://feta.grand-challenge.org/Data/), and organize the dataset directory structure as follows. \n\n    The organized M\u0026MS dataset can be downloaded at [Baidu Netdisk](https://pan.baidu.com/s/1ustJYI2V2qh-ZZLNu9R-WQ?pwd=2023 ).\n```\nyour/M\u0026MS_data_root/\n       train/\n            img/\n                A/\n                    A0S9V9_0.nii.gz\n                    ...\n                B/\n                C/\n                ...\n            lab/\n                A/\n                    A0S9V9_0_gt.nii.gz\n                    ...\n                B/\n                C/\n                ...\n       valid/\n            img/\n            lab/\n       test/\n           img/\n           lab/\n```\nThe network takes nii files as an input. The gt folder contains gray-scale images of the ground-truth, where the gray-scale level is the number of the class (0,1,...K).\n\n3. Adaptation to the target domain, for 2D dataset:\n\n```\npython run_2d_upl.py --config \"./config/train2d.cfg\"\n```\nfor 3D dataset:\n```\npython run_3d_upl.py --config \"./config/train3d.cfg\"\n```","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhilab-git%2Fupl-sfda","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhilab-git%2Fupl-sfda","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhilab-git%2Fupl-sfda/lists"}