{"id":20023297,"url":"https://github.com/cyanogenoid/dspn","last_synced_at":"2025-05-05T02:30:35.563Z","repository":{"id":78890559,"uuid":"191885058","full_name":"Cyanogenoid/dspn","owner":"Cyanogenoid","description":"[NeurIPS 2019] Deep Set Prediction Networks","archived":false,"fork":false,"pushed_at":"2020-09-18T00:50:48.000Z","size":683,"stargazers_count":100,"open_issues_count":2,"forks_count":18,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-08T15:05:48.383Z","etag":null,"topics":["deep-learning","neurips","neurips-2019","prediction","set"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1906.06565","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/Cyanogenoid.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-06-14T06:06:09.000Z","updated_at":"2024-03-08T10:23:49.000Z","dependencies_parsed_at":"2023-03-05T16:15:42.361Z","dependency_job_id":null,"html_url":"https://github.com/Cyanogenoid/dspn","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyanogenoid%2Fdspn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyanogenoid%2Fdspn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyanogenoid%2Fdspn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyanogenoid%2Fdspn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Cyanogenoid","download_url":"https://codeload.github.com/Cyanogenoid/dspn/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252427615,"owners_count":21746245,"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","neurips","neurips-2019","prediction","set"],"created_at":"2024-11-13T08:45:47.765Z","updated_at":"2025-05-05T02:30:35.554Z","avatar_url":"https://github.com/Cyanogenoid.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Set Prediction Networks\n\n![Overview of set optimisation on the example of CLEVR bounding box prediction](overview.png)\n\nThis is the official implementation of our NeurIPS 2019 paper [Deep Set Prediction Networks][0].\nWe propose a new way of predicting sets with a neural network that doesn't suffer from discontinuity issues.\nThis is done by backpropagating through a set encoder to act as a set decoder.\nYou can take a look at the [poster for NeurIPS 2019][4] or the [poster for the NeurIPS 2019 workshop on Sets \u0026 Partitions][5].\n\nTo use the decoder, you only need [`dspn.py`][1].\nYou can see how it is used in [`model.py`][2] with `build_net` and the `Net` class.\nFor details on the exact steps to reproduce the experiments, check out the README in the `dspn` directory.\nYou can download pre-trained models and the predictions thereof from the [Resources][3] page.\n\n# BibTeX entry\n\n```\n@inproceedings{zhang2019dspn,\n    author        = {Yan Zhang and Jonathon Hare and Adam Pr\\\"ugel-Bennett},\n    title         = {{Deep Set Prediction Networks}},\n    booktitle     = {Advances in Neural Information Processing Systems 32},\n    year          = {2019},\n    eprint        = {1906.06565},\n    url           = {https://arxiv.org/abs/1906.06565},\n}\n```\n\n\n[0]: https://arxiv.org/abs/1906.06565\n[1]: https://github.com/Cyanogenoid/dspn/blob/master/dspn.py\n[2]: https://github.com/Cyanogenoid/dspn/blob/master/dspn/model.py\n[3]: https://github.com/Cyanogenoid/dspn/releases/tag/resources\n[4]: https://www.cyanogenoid.com/files/dspn-poster.pdf\n[5]: https://www.cyanogenoid.com/files/dspn-workshop-poster.pdf\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyanogenoid%2Fdspn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcyanogenoid%2Fdspn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyanogenoid%2Fdspn/lists"}