https://github.com/ymd-h/b4tf
Mirror Repository of https://gitlab.com/ymd_h/b4tf
https://github.com/ymd-h/b4tf
bayesian-networks machine-learning python
Last synced: 12 months ago
JSON representation
Mirror Repository of https://gitlab.com/ymd_h/b4tf
- Host: GitHub
- URL: https://github.com/ymd-h/b4tf
- Owner: ymd-h
- License: mit
- Created: 2020-09-19T09:57:30.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-11-03T12:37:22.000Z (over 5 years ago)
- Last Synced: 2025-05-29T09:11:48.451Z (about 1 year ago)
- Topics: bayesian-networks, machine-learning, python
- Language: Python
- Homepage:
- Size: 555 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.org
- Changelog: CHANGELOG.org
- License: LICENSE
Awesome Lists containing this project
README
#+OPTIONS: ':nil *:t -:t ::t <:t H:3 \n:nil ^:t arch:headline
#+OPTIONS: author:t broken-links:nil c:nil creator:nil
#+OPTIONS: d:(not "LOGBOOK") date:t e:t email:nil f:t inline:t num:t
#+OPTIONS: p:nil pri:nil prop:nil stat:t tags:t tasks:t tex:t
#+OPTIONS: timestamp:t title:t toc:nil todo:nil |:t
#+title: Bayes Neural Network for TensorFlow (b4tf)
#+date: <2020-07-18 Sat>
#+author: Hiroyuki Yamada
#+LANGUAGE: en
#+SELECT_TAGS: export
#+EXCLUDE_TAGS: noexport
#+CREATOR: Emacs 26.1 (Org mode 9.1.14)
#+HUGO_WITH_LOCALE:
#+HUGO_FRONT_MATTER_FORMAT: toml
#+HUGO_LEVEL_OFFSET: 1
#+HUGO_PRESERVE_FILLING:
#+HUGO_DELETE_TRAILING_WS:
#+HUGO_SECTION: .
#+HUGO_BUNDLE:
#+HUGO_BASE_DIR: ./site
#+HUGO_CODE_FENCE:
#+HUGO_USE_CODE_FOR_KBD:
#+HUGO_PREFER_HYPHEN_IN_TAGS:
#+HUGO_ALLOW_SPACES_IN_TAGS:
#+HUGO_AUTO_SET_LASTMOD:
#+HUGO_CUSTOM_FRONT_MATTER:
#+HUGO_BLACKFRIDAY:
#+HUGO_FRONT_MATTER_KEY_REPLACE:
#+HUGO_DATE_FORMAT: %Y-%m-%dT%T+09:00
#+HUGO_PAIRED_SHORTCODES:
#+HUGO_PANDOC_CITATIONS:
#+BIBLIOGRAPHY:
#+HUGO_ALIASES:
#+HUGO_AUDIO:
#+DESCRIPTION:
#+HUGO_DRAFT:
#+HUGO_EXPIRYDATE:
#+HUGO_HEADLESS:
#+HUGO_IMAGES:
#+HUGO_ISCJKLANGUAGE:
#+KEYWORDS:
#+HUGO_LAYOUT:
#+HUGO_LASTMOD:
#+HUGO_LINKTITLE:
#+HUGO_LOCALE:
#+HUGO_MARKUP:
#+HUGO_MENU:
#+HUGO_MENU_OVERRIDE:
#+HUGO_OUTPUTS:
#+HUGO_PUBLISHDATE:
#+HUGO_SERIES:
#+HUGO_SLUG:
#+HUGO_TAGS:
#+HUGO_CATEGORIES:
#+HUGO_RESOURCES:
#+HUGO_TYPE:
#+HUGO_URL:
#+HUGO_VIDEOS:
#+HUGO_WEIGHT: auto
#+STARTUP: showall logdone
[[https://img.shields.io/gitlab/pipeline/ymd_h/b4tf.svg]]
[[https://img.shields.io/pypi/v/b4tf.svg]]
[[https://img.shields.io/pypi/l/b4tf.svg]]
[[https://img.shields.io/pypi/status/b4tf.svg]]
[[https://ymd_h.gitlab.io/b4tf/coverage/][https://gitlab.com/ymd_h/b4tf/badges/master/coverage.svg]]
#+attr_html: :width 100px
[[./site/static/images/logo.png]]
* Overview
b4tf is a Python module providing a set of bayesian neural network on
[[https://www.tensorflow.org/][TensorFlow]].
* DONE Installation
:PROPERTIES:
:EXPORT_HUGO_SECTION: installation
:EXPORT_FILE_NAME: _index
:EXPORT_HUGO_WEIGHT: 100
:END:
b4tf requires following softwares before installation
- [[https://www.tensorflow.org/][TensorFlow 2.x]]
- [[https://www.tensorflow.org/probability][TnesorFlow Probability]]
- Python 3.x
** Install from [[https://pypi.org/][PyPI]] (Recommended)
The following command installs b4tf together with other dependancies.
#+BEGIN_SRC shell
pip install b4tf
#+END_SRC
Depending on your environment, you might need =sudo= or =--user= flag
for installation.
** Install from source code
First, download source code manually or clone the repository;
#+begin_src shell
git clone https://gitlab.com/ymd_h/b4tf.git
#+end_src
Then you can install same way;
#+begin_src shell
cd b4tf
pip install .
#+end_src
* DONE Implemented Algorithms
:PROPERTIES:
:EXPORT_HUGO_SECTION: algorithms
:EXPORT_FILE_NAME: _index
:EXPORT_HUGO_WEIGHT: 200
:END:
Currently, b4tf implements following algorithms. We will implement
more.
- 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]])
- 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]])
* DONE Contributing to b4tf
CLOSED: [2020-01-17 Fri 23:09]
:PROPERTIES:
:EXPORT_HUGO_SECTION: contributing
:EXPORT_FILE_NAME: _index
:EXPORT_HUGO_WEIGHT: 300
:END:
Any contribution are very welcome!
** Making Community Larger
Bigger commumity makes development more active and improve b4tf.
- Star [[https://gitlab.com/ymd_h/b4tf][this GitLab repository]] (and/or [[https://github.com/ymd-h/b4tf][GitHub Mirror]])
- Publish your code using b4tf
- Share this repository to your friend and/or followers.
** Report Issue
When you have any problems or requests, you can check [[https://gitlab.com/ymd_h/b4tf/issues][issues on GitLab.com]].
If you still cannot find any information, you can open your own issue.
** Merge Request (Pull Request)
b4tf follows local rules:
- Branch Name
- "HotFix_***" for bug fix
- "Feature_***" for new feature implementation
- docstring
- Must for external API
- [[https://numpydoc.readthedocs.io/en/latest/format.html][Numpy Style]]
- Unit Test
- Put test code under "test/" directory
- Can test by =python -m unittest = command
- Continuous Integration on GitLab CI configured by ~.gitlab-ci.yaml~
- Open an issue and associate it to Merge Request
Step by step instruction for beginners is described at [[https://ymd_h.gitlab.io/b4tf/contributing/merge_request][here]].
* DONE Links
CLOSED: [2020-01-17 Fri 23:09]
:PROPERTIES:
:EXPORT_HUGO_SECTION: misc
:EXPORT_FILE_NAME: links
:END:
** b4tf sites
- [[https://ymd_h.gitlab.io/b4tf/][Project Site]]
- [[https://ymd_h.gitlab.io/b4tf/api/][Class Reference]]
- [[https://ymd_h.gitlab.io/b4tf/coverage/][Unit Test Coverage]]
- [[https://gitlab.com/ymd_h/b4tf][Main Repository]]
- [[https://github.com/ymd-h/b4tf][GitHub Mirror]]
- [[https://pypi.org/project/b4tf/][b4tf on PyPI]]
* DONE Lisence
:PROPERTIES:
:EXPORT_HUGO_SECTION: misc
:EXPORT_FILE_NAME: lisence
:END:
b4tf is available under MIT lisence.
#+INCLUDE: "./LICENSE" src