{"id":13737582,"url":"https://github.com/smkim7-kr/AdaMatch-pytorch","last_synced_at":"2025-05-08T14:33:04.123Z","repository":{"id":184568284,"uuid":"404425909","full_name":"smkim7-kr/AdaMatch-pytorch","owner":"smkim7-kr","description":"Unofficial implementation of \"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation\"","archived":false,"fork":false,"pushed_at":"2021-09-08T17:10:12.000Z","size":3128,"stargazers_count":8,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-15T06:32:05.937Z","etag":null,"topics":["computer-vision","deep-learning","domain-adaptation","semi-supervised-domain-adaptation","semi-supervised-learning","unsupervised-domain-adaptation"],"latest_commit_sha":null,"homepage":"","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/smkim7-kr.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}},"created_at":"2021-09-08T16:51:30.000Z","updated_at":"2024-07-25T23:01:13.000Z","dependencies_parsed_at":null,"dependency_job_id":"f854c25e-d8be-4fc4-894a-e80c2a1286c9","html_url":"https://github.com/smkim7-kr/AdaMatch-pytorch","commit_stats":null,"previous_names":["smkim7-kr/adamatch-pytorch"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smkim7-kr%2FAdaMatch-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smkim7-kr%2FAdaMatch-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smkim7-kr%2FAdaMatch-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smkim7-kr%2FAdaMatch-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/smkim7-kr","download_url":"https://codeload.github.com/smkim7-kr/AdaMatch-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253085768,"owners_count":21851696,"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":["computer-vision","deep-learning","domain-adaptation","semi-supervised-domain-adaptation","semi-supervised-learning","unsupervised-domain-adaptation"],"created_at":"2024-08-03T03:01:54.027Z","updated_at":"2025-05-08T14:33:03.717Z","avatar_url":"https://github.com/smkim7-kr.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# AdaMatch-pytorch\r\n\r\nThis is an unofficial implementation of [AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation](https://arxiv.org/abs/2106.04732). Official code is [here](https://github.com/google-research/adamatch) written by Google Research with Jax. [Paper summary](https://smkim7.notion.site/AdaMatch-A-Unified-Approach-to-Semi-Supervised-Learning-and-Domain-Adaptation-Korean-9e6e221cca5e46cb80b9d36e6153553c) and [video presentation](https://www.youtube.com/watch?v=VMZZNaHSTf4\u0026t=162s) are done by myself (in Korean unfortunately).\r\n\r\nStep-by-step explanations in Colab notebooks are [here](https://colab.research.google.com/drive/1FY67_4dzLxIcWVkJR6IzwhzKWBcfesO9#scrollTo=SRFCRNEoNerZ).\r\n\r\n### Requirements\r\n\r\nYou can easily install all requirements by the command\r\n\r\n```\r\npip install -r requirements.txt\r\n```\r\n\r\n### Datasets\r\n\r\nThe code supports source to target domain adaptation from SVHN to MNIST (part of DigitFive dataset presented in the paper) . \r\n\r\n### Training\r\n\r\n```\r\npython main.py --uratio 3 --tau 0.9\r\n```\r\n\r\nThe code includes different hyperparameters for config including\r\n\r\n* uratio (default=3): Ratio between source and target batch size (uratio * source = target)\r\n* tau (default=0.9): Pseudolabel threshold for Relative confidence threshold\r\n\r\nDefault all follows from the paper.\r\n\r\n### References\r\n\r\n* [AdaMatch-pytorch](https://github.com/zysymu/AdaMatch-pytorch) by zysymu\r\n\r\n```\r\n@article{berthelot2021adamatch,\r\n  title={AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation},\r\n  author={Berthelot, David and Roelofs, Rebecca and Sohn, Kihyuk and Carlini, Nicholas and Kurakin, Alex},\r\n  journal={arXiv preprint arXiv:2106.04732},\r\n  year={2021}\r\n}\r\n```\r\n\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmkim7-kr%2FAdaMatch-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsmkim7-kr%2FAdaMatch-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmkim7-kr%2FAdaMatch-pytorch/lists"}