https://github.com/harry24k/bayesian-neural-network-pytorch

PyTorch implementation of bayesian neural network [torchbnn]
https://github.com/harry24k/bayesian-neural-network-pytorch

bayesian deep-learning neural-network pytorch

Last synced: 3 days ago
JSON representation

PyTorch implementation of bayesian neural network [torchbnn]

• Host: GitHub
• URL: https://github.com/harry24k/bayesian-neural-network-pytorch
• Owner: Harry24k
• License: mit
• Created: 2019-09-04T14:28:12.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2024-07-25T10:55:11.000Z (5 months ago)
• Last Synced: 2024-12-14T15:05:31.699Z (10 days ago)
• Topics: bayesian, deep-learning, neural-network, pytorch
• Language: Python
• Homepage:
• Size: 22.2 MB
• Stars: 502
• Watchers: 12
• Forks: 75
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Bayesian-Neural-Network-Pytorch



  

  

  



This is a lightweight repository of bayesian neural network for PyTorch.

## Usage

### :clipboard: Dependencies

- torch 1.2.0

- python 3.6

### :hammer: Installation

- `pip install torchbnn` or

- `git clone https://github.com/Harry24k/bayesian-neural-network-pytorch`

```python

import torchbnn

```

### :rocket: Demos

* **Bayesian Neural Network Regression** ([code](https://github.com/Harry24k/bayesian-neural-network-pytorch/blob/master/demos/Bayesian%20Neural%20Network%20Regression.ipynb)): 

In this demo, two-layer bayesian neural network is constructed and trained on simple custom data. It shows how bayesian-neural-network works and randomness of the model.

* **Bayesian Neural Network Classification** ([code](https://github.com/Harry24k/bayesian-neural-network-pytorch/blob/master/demos/Bayesian%20Neural%20Network%20Classification.ipynb)): 

To classify Iris data, in this demo, two-layer bayesian neural network is constructed and trained on the Iris data. It shows how bayesian-neural-network works and randomness of the model.

* **Convert to Bayesian Neural Network** ([code](https://github.com/Harry24k/bayesian-neural-network-pytorch/blob/master/demos/Convert%20to%20Bayesian%20Neural%20Network.ipynb)): 

To convert a basic neural network to a bayesian neural network, this demo shows how `nonbayes_to_bayes` and `bayes_to_nonbayes` work.

* **Freeze Bayesian Neural Network** ([code](https://github.com/Harry24k/bayesian-neural-network-pytorch/blob/master/demos/Freeze%20Bayesian%20Neural%20Network.ipynb)): 

To freeze a bayesian neural network, which means force a bayesian neural network to output same result for same input, this demo shows the effect of `freeze` and `unfreeze`.

## Citation

If you use this package, please cite the following BibTex (SemanticScholar, GoogleScholar):

```

@article{lee2022graddiv,

  title={Graddiv: Adversarial robustness of randomized neural networks via gradient diversity regularization},

  author={Lee, Sungyoon and Kim, Hoki and Lee, Jaewook},

  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},

  year={2022},

  publisher={IEEE}

}

```

## :mag_right: Update Records

Here is [update records](Update%20Records.md) of this package.

## Thanks to

* @kumar-shridhar [github:PyTorch-BayesianCNN](https://github.com/kumar-shridhar/PyTorch-BayesianCNN)

* @xuanqing94 [github:BayesianDefense](https://github.com/xuanqing94/BayesianDefense)