{"id":21169760,"url":"https://github.com/andreasgrv/sigmoid-bottleneck","last_synced_at":"2025-07-09T19:32:02.106Z","repository":{"id":200759518,"uuid":"699278336","full_name":"andreasgrv/sigmoid-bottleneck","owner":"andreasgrv","description":"Sparse Multi Label Classification","archived":false,"fork":false,"pushed_at":"2023-10-17T13:28:12.000Z","size":558,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-05-02T02:35:34.188Z","etag":null,"topics":[],"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/andreasgrv.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}},"created_at":"2023-10-02T10:07:16.000Z","updated_at":"2024-02-20T10:05:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"8046aa90-3f27-485c-aa25-e465ee17e7d9","html_url":"https://github.com/andreasgrv/sigmoid-bottleneck","commit_stats":null,"previous_names":["andreasgrv/sigmoid-bottleneck"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreasgrv%2Fsigmoid-bottleneck","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreasgrv%2Fsigmoid-bottleneck/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreasgrv%2Fsigmoid-bottleneck/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreasgrv%2Fsigmoid-bottleneck/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andreasgrv","download_url":"https://codeload.github.com/andreasgrv/sigmoid-bottleneck/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225587808,"owners_count":17492632,"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":[],"created_at":"2024-11-20T15:53:37.454Z","updated_at":"2024-11-20T15:53:38.105Z","avatar_url":"https://github.com/andreasgrv.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Sparse Multi-Label Classification (spmlbl)\n\nHerein we provide the code to reproduce our results for the paper:\n\n[Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification](https://arxiv.org/abs/2310.10443)\n\n# Installation\n\nBelow installation is for main library.\n\n## Install Python Dependencies\n```bash\npython3.8 -m venv .env\nsource .env/bin/activate\n# Adapt cuda in requirements to your use case\npip install -r requirements.txt\npip install -e .\n# NOTE: For each specific dataset you may need to install more libraries\n# See README.md file in each experiment section\n```\n\n## Set Environment Variables\n\n```bash\n# Avoid pytorch using too many threads\nexport OMP_NUM_THREADS=1\nexport MKL_NUM_THREADS=1\n\n# Random seed - needed for exps\nexport SEED=0\n# What device to run models on\nexport MLBL_DEVICE=\"cuda:0\"\n# Number of threads\nexport MLBL_NUM_PROC=10\n```\n\n## Install [Gurobi](https://www.gurobi.com/academia/academic-program-and-licenses/)\n\nThe linear programming algorithm that detects (un)argmaxable label assignments depends on Gurobi.\nIt requires a license, see link above.\n\n\n## Run Tests\n\nTests require dependencies and Gurobi.\n\n```bash\npy.test tests\n```\n\n## Experiments\n\nFor each dataset, see the `README.md` file in the corresponding folder under experiments.\n\n* [MIMIC-III](experiments/mimic/README.md)\n* [BioASQ Task A](experiments/bioasq/README.md)\n* [OpenImages v6](experiments/openimagesv6/README.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandreasgrv%2Fsigmoid-bottleneck","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandreasgrv%2Fsigmoid-bottleneck","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandreasgrv%2Fsigmoid-bottleneck/lists"}