{"id":13422270,"url":"https://github.com/eveningdong/DAOSL","last_synced_at":"2025-03-15T11:31:33.536Z","repository":{"id":129457181,"uuid":"157152506","full_name":"eveningdong/DAOSL","owner":"eveningdong","description":"Implementation of Domain Adaption in One-Shot Learning","archived":false,"fork":false,"pushed_at":"2019-03-11T03:56:21.000Z","size":14612,"stargazers_count":15,"open_issues_count":0,"forks_count":6,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-08-10T07:01:17.127Z","etag":null,"topics":["domain-adaptation","one-shot-learning","reinforcement-learning","slim","tensorflow"],"latest_commit_sha":null,"homepage":"","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/eveningdong.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":"2018-11-12T03:40:56.000Z","updated_at":"2024-07-09T11:56:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"cf5298be-7925-4a26-8e7f-ff547dc84f0d","html_url":"https://github.com/eveningdong/DAOSL","commit_stats":null,"previous_names":["leonndong/daosl"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eveningdong%2FDAOSL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eveningdong%2FDAOSL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eveningdong%2FDAOSL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eveningdong%2FDAOSL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eveningdong","download_url":"https://codeload.github.com/eveningdong/DAOSL/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243724954,"owners_count":20337655,"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":["domain-adaptation","one-shot-learning","reinforcement-learning","slim","tensorflow"],"created_at":"2024-07-30T23:00:40.841Z","updated_at":"2025-03-15T11:31:32.357Z","avatar_url":"https://github.com/eveningdong.png","language":"Python","funding_links":[],"categories":["Domain adaption in one-shot learning. ECML-PKDD 2018"],"sub_categories":["reviewer comment at [OpenReview](https://openreview.net/forum?id=ByGOuo0cYm)"],"readme":"# Domain Adaption in One-Shot Learning\n\nImplementation of Domain Adaption in One-Shot Learning.\n\n## Paper\nYou can find our paper at [Springer](https://link.springer.com/chapter/10.1007/978-3-030-10925-7_35) or [PDF](https://github.com/NanqingD/DAOSL/blob/master/ECML_2018_Camera_Ready_Final.pdf).\n\n## Citation\nIf you find DAOSL useful in your research, please consider to cite:\n\n@inproceedings{dong2018domain, \n  title={Domain adaption in one-shot learning}, \n  author={Dong, Nanqing and Eric P. Xing}, \n  booktitle={Joint European Conference on Machine Learning and Knowledge Discovery in Databases},\n  pages={573--588},\n  year={2018},\n  organization={Springer}\n}\n\n## Setup\n### Requirements\n```\npython 3.5\ntensorflow 1.8\nCUDA  9.0\ncuDNN 7.0\n```\n\n### Installation\n```\nsh setup.sh\n```\n\n## Training\nTrain one-shot classifier for 5-way 1-shot learning.\n```\npython3 convert_data.py --data-name=omniglot\npython3 convert_data.py --data-name=emnist --num-target-examples=20\npython3 train_one_shot.py --exp-name=one_shot --source=omniglot --target=emnist_20 --num-ways=5\n```\n\nTrain adversarial domain adaption (ADA) for 5-way 1-shot learning.\n```\npython3 convert_data.py --data-name=omniglot\npython3 convert_data.py --data-name=emnist --num-target-examples=20\npython3 train_ada.py --exp-name=ada --source=omniglot --target=emnist_20 --num-ways=5 --la=0.001\n```\n\nTrain adversarial domain adaption (ADA) with reinforced sample selection (RSS) for 5-way 1-shot learning.\n```\npython3 convert_data.py --data-name=chars\npython3 convert_data.py --data-name=sim\npython3 convert_data.py --data-name=dis\npython3 train_rss.py --exp-name=rss --num-ways=5 --la=0.001 --gamma=0.1\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feveningdong%2FDAOSL","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feveningdong%2FDAOSL","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feveningdong%2FDAOSL/lists"}