Bayes Neural Network for TensorFlow (b4tf)

1 Overview

b4tf is a Python module providing a set of bayesian neural network on TensorFlow.

2 Installation

b4tf requires following softwares before installation

• TensorFlow 2.x
• TnesorFlow Probability
• Python 3.x

2.1 Install from PyPI (Recommended)

The following command installs b4tf together with other dependancies.

pip install b4tf

Depending on your environment, you might need sudo or --user flag for installation.

2.2 Install from source code

First, download source code manually or clone the repository;

git clone https://gitlab.com/ymd_h/b4tf.git

Then you can install same way;

cd b4tf
pip install .

3 Implemented Algorithms

Currently, b4tf implements following algorithms. We will implement more.

• Probabilistic Backpropagation (PBP) (Paper, Doc, API)
• Monte Carlo Batch Normalization (MCBN) (Paper, Doc, API)

4 Contributing to b4tf

Any contribution are very welcome!

4.1 Making Community Larger

Bigger commumity makes development more active and improve b4tf.

• Star this GitLab repository (and/or GitHub Mirror)
• Publish your code using b4tf
• Share this repository to your friend and/or followers.

4.2 Report Issue

When you have any problems or requests, you can check issues on GitLab.com. If you still cannot find any information, you can open your own issue.

4.3 Merge Request (Pull Request)

b4tf follows local rules:

• Branch Name
  • “HotFix_***” for bug fix
  • “Feature_***” for new feature implementation
• docstring
  • Must for external API
  • Numpy Style
• Unit Test
  • Put test code under “test/” directory
  • Can test by python -m unittest <Your Test Code> 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 here.

5 Links

5.1 b4tf sites

• Project Site
  • Class Reference
  • Unit Test Coverage
• Main Repository
• GitHub Mirror
• b4tf on PyPI

6 Lisence

b4tf is available under MIT lisence.