{"id":18358444,"url":"https://github.com/wiseodd/bayesian_ood_training","last_synced_at":"2026-02-13T00:07:09.942Z","repository":{"id":50674933,"uuid":"308006302","full_name":"wiseodd/bayesian_ood_training","owner":"wiseodd","description":null,"archived":false,"fork":false,"pushed_at":"2023-08-18T18:47:08.000Z","size":11124,"stargazers_count":9,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-10-11T02:25:35.640Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wiseodd.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}},"created_at":"2020-10-28T12:16:36.000Z","updated_at":"2024-01-06T17:51:09.000Z","dependencies_parsed_at":"2022-08-28T18:53:33.450Z","dependency_job_id":null,"html_url":"https://github.com/wiseodd/bayesian_ood_training","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/wiseodd/bayesian_ood_training","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wiseodd%2Fbayesian_ood_training","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wiseodd%2Fbayesian_ood_training/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wiseodd%2Fbayesian_ood_training/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wiseodd%2Fbayesian_ood_training/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wiseodd","download_url":"https://codeload.github.com/wiseodd/bayesian_ood_training/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wiseodd%2Fbayesian_ood_training/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29388029,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-13T00:02:39.825Z","status":"ssl_error","status_checked_at":"2026-02-13T00:00:20.807Z","response_time":55,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2024-11-05T22:17:53.175Z","updated_at":"2026-02-13T00:07:09.915Z","avatar_url":"https://github.com/wiseodd.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Bayesian OOD Training\n\nCode for the AISTATS 2022 paper titled \"Being a Bit Frequentist Improves Bayesian Neural Networks\" by Agustinus Kristiadi, Matthias Hein, and Philipp Hennig.\n\n## Setting up:\n\n1. Run: `conda create --name ENV_NAME --file conda_env.txt`.\n2. Then: `conda activate ENV_NAME`.\n3. Install PyTorch and TorchVision (\u003chttps://pytorch.org/get-started/locally/\u003e).\n4. Set the dataset path in `util/dataloaders.py`, line 30 (`path = os.path.expanduser('~/Datasets')`).\n5. Follow the instruction here to obtain the NLP datasets: \u003chttps://github.com/hendrycks/outlier-exposure/tree/master/NLP_classification\u003e.\n\n\n## Reproducing the paper's results:\n\n1. Model training: run `train.sh`, `train_nlp.sh`, and `train_aux.sh`.\n2. Run `eval.sh` and `eval_nlp.sh` to gather experiments data.\n3. Run `aggregate_*.py` to create the tables in the paper based on the previous data.\n4. Run `plot_*.py` to create figures for dataset shift experiments.\n\n## Citing the paper:\n\n```\n@inproceedings{kristiadi2022frequentist,\n  title={Being a Bit Frequentist Improves {B}ayesian Neural Networks},\n  author={Kristiadi, Agustinus and Hein, Matthias and Hennig, Philipp},\n  booktitle={AISTATS},\n  year={2022}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwiseodd%2Fbayesian_ood_training","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwiseodd%2Fbayesian_ood_training","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwiseodd%2Fbayesian_ood_training/lists"}