{"id":16568136,"url":"https://github.com/wogong/pytorch-dann","last_synced_at":"2025-10-17T16:01:17.161Z","repository":{"id":44446628,"uuid":"132776797","full_name":"wogong/pytorch-dann","owner":"wogong","description":"A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation","archived":false,"fork":false,"pushed_at":"2020-09-30T19:21:38.000Z","size":100,"stargazers_count":148,"open_issues_count":2,"forks_count":19,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-02-27T13:18:38.710Z","etag":null,"topics":["deep-learning","domain-adaptation","generative-adversarial-network","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/wogong.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":"2018-05-09T15:24:51.000Z","updated_at":"2024-11-25T01:32:55.000Z","dependencies_parsed_at":"2022-08-12T11:11:05.841Z","dependency_job_id":null,"html_url":"https://github.com/wogong/pytorch-dann","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/wogong%2Fpytorch-dann","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wogong%2Fpytorch-dann/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wogong%2Fpytorch-dann/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wogong%2Fpytorch-dann/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wogong","download_url":"https://codeload.github.com/wogong/pytorch-dann/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243830912,"owners_count":20354848,"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":["deep-learning","domain-adaptation","generative-adversarial-network","pytorch"],"created_at":"2024-10-11T21:08:26.665Z","updated_at":"2025-10-17T16:01:11.808Z","avatar_url":"https://github.com/wogong.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PyTorch-DANN\n\nA PyTorch implementation for paper *[Unsupervised Domain Adaptation by Backpropagation](http://sites.skoltech.ru/compvision/projects/grl/)*\n\n    InProceedings (icml2015-ganin15)\n    Ganin, Y. \u0026 Lempitsky, V.\n    Unsupervised Domain Adaptation by Backpropagation\n    Proceedings of the 32nd International Conference on Machine Learning, 2015\n\n## Environment\n\n- Python 3.6\n- PyTorch 1.0\n\n## Note\n\n- `MNISTmodel()`\n    - basically the same network structure as proposed in the paper, expect for adding dropout layer in feature extractor\n    - large gap exsits between with and w/o dropout layer\n    - better result than paper\n- `SVHNmodel()`\n    - network structure proposed in the paper may be wrong for both 32x32 and 28x28 inputs\n    - change last conv layer's filter to 4x4, get similar(actually higher) result\n- `GTSRBmodel()`\n- `AlexModel`\n    - not successful, mainly due to the pretrained model difference\n\n## Result\n\n|                      | MNIST-MNISTM   | SVHN-MNIST | SYNDIGITS-SVHN | SYNSIGNS-GTSRB |\n| :------------------: | :------------: | :--------: |:-------------: |:-------------: |\n| Source Only          |   0.5225       |  0.5490    | 0.8674         | 0.7900         |\n| DANN(paper)          |   0.7666       |  0.7385    | 0.9109         | 0.8865         |\n| This Repo Source Only|   -            |  -         | -              | 0.9100         |\n| This Repo            |   0.8400       |  0.7339    | 0.8200         | -              |\n\n|                      | AMAZON-WEBVCAM |  DSLR-WEBCAM | WEBCAM-DSLR |\n| :------------------: | :------------: |:-----------: |:----------: |\n| Source Only          |   0.6420       |  0.9610      | 0.9780      |\n| DANN(paper)          |   0.7300       |  0.9640      | 0.9920      |\n| This Repo Source Only|   -            |  -           | -           |\n| This Repo            |   0.6528       |  -           | -           |\n\n## Credit\n\n- \u003chttps://github.com/fungtion/DANN\u003e\n- \u003chttps://github.com/corenel/torchsharp\u003e\n- \u003chttps://github.com/corenel/pytorch-starter-kit\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwogong%2Fpytorch-dann","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwogong%2Fpytorch-dann","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwogong%2Fpytorch-dann/lists"}