{"id":19071757,"url":"https://github.com/blackhc/batchbald","last_synced_at":"2025-04-07T12:06:10.565Z","repository":{"id":147711524,"uuid":"191570776","full_name":"BlackHC/BatchBALD","owner":"BlackHC","description":"Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.","archived":false,"fork":false,"pushed_at":"2024-06-05T17:48:25.000Z","size":13101,"stargazers_count":238,"open_issues_count":1,"forks_count":55,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-31T11:02:47.739Z","etag":null,"topics":["activelearning","deep-learning","machine-learning","reproduction-code"],"latest_commit_sha":null,"homepage":"https://blackhc.github.io/BatchBALD/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BlackHC.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":"2019-06-12T12:54:18.000Z","updated_at":"2025-03-22T17:06:40.000Z","dependencies_parsed_at":"2024-11-16T06:04:56.694Z","dependency_job_id":"af52fd51-cbac-45ac-b6d1-9d515d6c9573","html_url":"https://github.com/BlackHC/BatchBALD","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/BlackHC%2FBatchBALD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlackHC%2FBatchBALD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlackHC%2FBatchBALD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BlackHC%2FBatchBALD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BlackHC","download_url":"https://codeload.github.com/BlackHC/BatchBALD/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247648977,"owners_count":20972945,"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":["activelearning","deep-learning","machine-learning","reproduction-code"],"created_at":"2024-11-09T01:30:42.511Z","updated_at":"2025-04-07T12:06:10.542Z","avatar_url":"https://github.com/BlackHC.png","language":"Python","readme":"# BatchBALD\n\n**Note:** A more modular re-implementation can be found at https://github.com/BlackHC/batchbald_redux.\n\n---\n\nThis is the code drop for our paper \n[BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://arxiv.org/abs/1906.08158).\n\nThe code comes as is.\n\nSee https://github.com/BlackHC/batchbald_redux and https://blackhc.github.io/batchbald_redux/ for a reimplementation.\n\nElementAI's Baal framework also supports BatchBALD: https://github.com/ElementAI/baal/. \n\nPlease cite us:\n\n```\n@misc{kirsch2019batchbald,\n    title={BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning},\n    author={Andreas Kirsch and Joost van Amersfoort and Yarin Gal},\n    year={2019},\n    eprint={1906.08158},\n    archivePrefix={arXiv},\n    primaryClass={cs.LG}\n}\n```\n\n## How to run it\n\nMake sure you install all requirements using\n\n```\nconda install pytorch torchvision cudatoolkit=10.0 -c pytorch\npip install -r requirements.txt\n```\n\nand you can start an experiment using:\n\n```\npython src/run_experiment.py --quickquick --num_inference_samples 10 --available_sample_k 40\n```\n\nwhich starts an experiment on a subset of MNIST with 10 MC dropout samples and acquisition size 40.\n\nHave fun playing around with it!\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblackhc%2Fbatchbald","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fblackhc%2Fbatchbald","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblackhc%2Fbatchbald/lists"}