{"id":20271733,"url":"https://github.com/ymd-h/b4tf","last_synced_at":"2025-06-12T22:05:44.223Z","repository":{"id":151958667,"uuid":"296837791","full_name":"ymd-h/b4tf","owner":"ymd-h","description":"Mirror Repository of https://gitlab.com/ymd_h/b4tf","archived":false,"fork":false,"pushed_at":"2020-11-03T12:37:22.000Z","size":568,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-29T09:11:48.451Z","etag":null,"topics":["bayesian-networks","machine-learning","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"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/ymd-h.png","metadata":{"files":{"readme":"README.org","changelog":"CHANGELOG.org","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":"2020-09-19T09:57:30.000Z","updated_at":"2022-09-09T13:20:30.000Z","dependencies_parsed_at":"2023-06-10T08:30:18.093Z","dependency_job_id":null,"html_url":"https://github.com/ymd-h/b4tf","commit_stats":null,"previous_names":[],"tags_count":20,"template":false,"template_full_name":null,"purl":"pkg:github/ymd-h/b4tf","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ymd-h%2Fb4tf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ymd-h%2Fb4tf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ymd-h%2Fb4tf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ymd-h%2Fb4tf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ymd-h","download_url":"https://codeload.github.com/ymd-h/b4tf/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ymd-h%2Fb4tf/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259539135,"owners_count":22873341,"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":["bayesian-networks","machine-learning","python"],"created_at":"2024-11-14T12:39:14.734Z","updated_at":"2025-06-12T22:05:44.176Z","avatar_url":"https://github.com/ymd-h.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"#+OPTIONS: ':nil *:t -:t ::t \u003c:t H:3 \\n:nil ^:t arch:headline\n#+OPTIONS: author:t broken-links:nil c:nil creator:nil\n#+OPTIONS: d:(not \"LOGBOOK\") date:t e:t email:nil f:t inline:t num:t\n#+OPTIONS: p:nil pri:nil prop:nil stat:t tags:t tasks:t tex:t\n#+OPTIONS: timestamp:t title:t toc:nil todo:nil |:t\n#+title: Bayes Neural Network for TensorFlow (b4tf)\n#+date: \u003c2020-07-18 Sat\u003e\n#+author: Hiroyuki Yamada\n#+LANGUAGE: en\n#+SELECT_TAGS: export\n#+EXCLUDE_TAGS: noexport\n#+CREATOR: Emacs 26.1 (Org mode 9.1.14)\n\n#+HUGO_WITH_LOCALE:\n#+HUGO_FRONT_MATTER_FORMAT: toml\n#+HUGO_LEVEL_OFFSET: 1\n#+HUGO_PRESERVE_FILLING:\n#+HUGO_DELETE_TRAILING_WS:\n#+HUGO_SECTION: .\n#+HUGO_BUNDLE:\n#+HUGO_BASE_DIR: ./site\n#+HUGO_CODE_FENCE:\n#+HUGO_USE_CODE_FOR_KBD:\n#+HUGO_PREFER_HYPHEN_IN_TAGS:\n#+HUGO_ALLOW_SPACES_IN_TAGS:\n#+HUGO_AUTO_SET_LASTMOD:\n#+HUGO_CUSTOM_FRONT_MATTER:\n#+HUGO_BLACKFRIDAY:\n#+HUGO_FRONT_MATTER_KEY_REPLACE:\n#+HUGO_DATE_FORMAT: %Y-%m-%dT%T+09:00\n#+HUGO_PAIRED_SHORTCODES:\n#+HUGO_PANDOC_CITATIONS:\n#+BIBLIOGRAPHY:\n#+HUGO_ALIASES:\n#+HUGO_AUDIO:\n#+DESCRIPTION:\n#+HUGO_DRAFT:\n#+HUGO_EXPIRYDATE:\n#+HUGO_HEADLESS:\n#+HUGO_IMAGES:\n#+HUGO_ISCJKLANGUAGE:\n#+KEYWORDS:\n#+HUGO_LAYOUT:\n#+HUGO_LASTMOD:\n#+HUGO_LINKTITLE:\n#+HUGO_LOCALE:\n#+HUGO_MARKUP:\n#+HUGO_MENU:\n#+HUGO_MENU_OVERRIDE:\n#+HUGO_OUTPUTS:\n#+HUGO_PUBLISHDATE:\n#+HUGO_SERIES:\n#+HUGO_SLUG:\n#+HUGO_TAGS:\n#+HUGO_CATEGORIES:\n#+HUGO_RESOURCES:\n#+HUGO_TYPE:\n#+HUGO_URL:\n#+HUGO_VIDEOS:\n#+HUGO_WEIGHT: auto\n\n#+STARTUP: showall logdone\n\n[[https://img.shields.io/gitlab/pipeline/ymd_h/b4tf.svg]]\n[[https://img.shields.io/pypi/v/b4tf.svg]]\n[[https://img.shields.io/pypi/l/b4tf.svg]]\n[[https://img.shields.io/pypi/status/b4tf.svg]]\n[[https://ymd_h.gitlab.io/b4tf/coverage/][https://gitlab.com/ymd_h/b4tf/badges/master/coverage.svg]]\n\n#+attr_html: :width 100px\n[[./site/static/images/logo.png]]\n\n\n* Overview\nb4tf is a Python module providing a set of bayesian neural network on\n[[https://www.tensorflow.org/][TensorFlow]].\n\n\n* DONE Installation\n:PROPERTIES:\n:EXPORT_HUGO_SECTION: installation\n:EXPORT_FILE_NAME: _index\n:EXPORT_HUGO_WEIGHT: 100\n:END:\nb4tf requires following softwares before installation\n\n- [[https://www.tensorflow.org/][TensorFlow 2.x]]\n- [[https://www.tensorflow.org/probability][TnesorFlow Probability]]\n- Python 3.x\n\n** Install from [[https://pypi.org/][PyPI]] (Recommended)\n\nThe following command installs b4tf together with other dependancies.\n\n#+BEGIN_SRC shell\npip install b4tf\n#+END_SRC\n\nDepending on your environment, you might need =sudo= or =--user= flag\nfor installation.\n\n** Install from source code\n\nFirst, download source code manually or clone the repository;\n\n#+begin_src shell\ngit clone https://gitlab.com/ymd_h/b4tf.git\n#+end_src\n\nThen you can install same way;\n\n#+begin_src shell\ncd b4tf\npip install .\n#+end_src\n\n* DONE Implemented Algorithms\n:PROPERTIES:\n:EXPORT_HUGO_SECTION: algorithms\n:EXPORT_FILE_NAME: _index\n:EXPORT_HUGO_WEIGHT: 200\n:END:\n\nCurrently, b4tf implements following algorithms. We will implement\nmore.\n\n- Probabilistic Backpropagation (PBP) ([[https://arxiv.org/abs/1502.05336][Paper]], [[https://ymd_h.gitlab.io/b4tf/algorithms/pbp][Doc]], [[https://ymd_h.gitlab.io/b4tf/api/b4tf.models.pbp.html#b4tf.models.pbp.PBP][API]])\n- Monte Carlo Batch Normalization (MCBN) ([[https://arxiv.org/abs/1802.06455][Paper]], [[https://ymd_h.gitlab.io/b4tf/algorithms/mcbn/][Doc]], [[https://ymd_h.gitlab.io/b4tf/api/b4tf.models.mcbn.html#b4tf.models.mcbn.MCBN][API]])\n\n\n* DONE Contributing to b4tf\nCLOSED: [2020-01-17 Fri 23:09]\n:PROPERTIES:\n:EXPORT_HUGO_SECTION: contributing\n:EXPORT_FILE_NAME: _index\n:EXPORT_HUGO_WEIGHT: 300\n:END:\n\nAny contribution are very welcome!\n\n** Making Community Larger\nBigger commumity makes development more active and improve b4tf.\n\n- Star [[https://gitlab.com/ymd_h/b4tf][this GitLab repository]] (and/or [[https://github.com/ymd-h/b4tf][GitHub Mirror]])\n- Publish your code using b4tf\n- Share this repository to your friend and/or followers.\n\n\n** Report Issue\nWhen you have any problems or requests, you can check [[https://gitlab.com/ymd_h/b4tf/issues][issues on GitLab.com]].\nIf you still cannot find any information, you can open your own issue.\n\n** Merge Request (Pull Request)\n\nb4tf follows local rules:\n- Branch Name\n  - \"HotFix_***\" for bug fix\n  - \"Feature_***\" for new feature implementation\n- docstring\n  - Must for external API\n  - [[https://numpydoc.readthedocs.io/en/latest/format.html][Numpy Style]]\n- Unit Test\n  - Put test code under \"test/\" directory\n  - Can test by =python -m unittest \u003cYour Test Code\u003e= command\n  - Continuous Integration on GitLab CI configured by ~.gitlab-ci.yaml~\n- Open an issue and associate it to Merge Request\n\nStep by step instruction for beginners is described at [[https://ymd_h.gitlab.io/b4tf/contributing/merge_request][here]].\n\n* DONE Links\nCLOSED: [2020-01-17 Fri 23:09]\n:PROPERTIES:\n:EXPORT_HUGO_SECTION: misc\n:EXPORT_FILE_NAME: links\n:END:\n\n** b4tf sites\n- [[https://ymd_h.gitlab.io/b4tf/][Project Site]]\n  - [[https://ymd_h.gitlab.io/b4tf/api/][Class Reference]]\n  - [[https://ymd_h.gitlab.io/b4tf/coverage/][Unit Test Coverage]]\n- [[https://gitlab.com/ymd_h/b4tf][Main Repository]]\n- [[https://github.com/ymd-h/b4tf][GitHub Mirror]]\n- [[https://pypi.org/project/b4tf/][b4tf on PyPI]]\n\n\n* DONE Lisence\n:PROPERTIES:\n:EXPORT_HUGO_SECTION: misc\n:EXPORT_FILE_NAME: lisence\n:END:\nb4tf is available under MIT lisence.\n\n#+INCLUDE: \"./LICENSE\" src\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fymd-h%2Fb4tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fymd-h%2Fb4tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fymd-h%2Fb4tf/lists"}