{"id":20640169,"url":"https://github.com/wondervictor/dpl.pytorch","last_synced_at":"2025-07-13T19:41:04.769Z","repository":{"id":71143923,"uuid":"129212689","full_name":"wondervictor/dpl.pytorch","owner":"wondervictor","description":"Pytorch Implementation for \"Deep Patch Learning for Weakly Supervised Object Classification and Discovery\"","archived":false,"fork":false,"pushed_at":"2018-07-22T09:31:10.000Z","size":934,"stargazers_count":7,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-15T22:58:49.475Z","etag":null,"topics":["computer-vision","deep-learning","object-detection","weakly-supervised-detection","weakly-supervised-learning"],"latest_commit_sha":null,"homepage":null,"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/wondervictor.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":"2018-04-12T07:42:31.000Z","updated_at":"2023-06-28T00:38:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"e68a234c-23c4-4351-8f73-21331f94b708","html_url":"https://github.com/wondervictor/dpl.pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/wondervictor/dpl.pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wondervictor%2Fdpl.pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wondervictor%2Fdpl.pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wondervictor%2Fdpl.pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wondervictor%2Fdpl.pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wondervictor","download_url":"https://codeload.github.com/wondervictor/dpl.pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wondervictor%2Fdpl.pytorch/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265197629,"owners_count":23726428,"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","object-detection","weakly-supervised-detection","weakly-supervised-learning"],"created_at":"2024-11-16T15:28:13.611Z","updated_at":"2025-07-13T19:41:04.728Z","avatar_url":"https://github.com/wondervictor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# dpl.pytorch\nPytorch Implementation for \"Deep Patch Learning for Weakly Supervised Object Classification and Discovery\" [paper](https://arxiv.org/abs/1705.02429)\n\n## Results\n\n**PASCAL VOC2012 Testset**\n\n**mAP: 0.90240**\n\n|Class|aeroplane|bicycle|bird   |boat   |bottle |bus    |car    |cat    |chair  |cow    |\n|-----|---------|-------|-------|-------|-------|-------|-------|-------|-------|-------|\n|AP   |0.98400  |0.92760|0.95630|0.93490|0.77990|0.92200|0.90910|0.97970|0.81800|0.90490|\n|Class|diningtable|dog    |horse |motorbike|person |pottedplant|sheep  |sofa   |train  |tvmonitor|\n|AP   |0.79660    |0.97180|0.96420|0.94030   |0.97750|0.70770    |0.92720|0.77180|0.97240|0.90220|\n\n## Training\n\n* Compling libs for this framework\n\n```bash\n\ncd lib/model/\ncd roi_align/ \u0026\u0026 ./make.sh\ncd roi_pooling \u0026\u0026 ./make.sh\ncd spmmax_pooling \u0026\u0026 ./make.sh\n\n```\n\n* train\n\n```bash\npython train.py --imageset [train, trainval] --basemodel [vgg, resnet34, resnet50] --data_dir \u003cData Directory Path\u003e\n```\n\n* proposal\n    - densebox sampling\n    - selective search\n \n## SPMMAX Pooling For **PyTorch**\n\nwritten as a PyTorch Extension and supported CUDA\n\nsee: `./lib/model/spmmax_pooling`\n\n\n## Licence\n\n**This project is under MIT Licence**","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwondervictor%2Fdpl.pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwondervictor%2Fdpl.pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwondervictor%2Fdpl.pytorch/lists"}