https://github.com/testingautomated-usi/uncertainty-wizard

Uncertainty-Wizard is a plugin on top of tensorflow.keras, allowing to easily and efficiently create uncertainty-aware deep neural networks. Also useful if you want to train multiple small models in parallel.
https://github.com/testingautomated-usi/uncertainty-wizard

keras keras-tensorflow testing uncertainty uncertainty-neural-networks uncertainty-quantification

Last synced: about 2 months ago
JSON representation

Uncertainty-Wizard is a plugin on top of tensorflow.keras, allowing to easily and efficiently create uncertainty-aware deep neural networks. Also useful if you want to train multiple small models in parallel.

• Host: GitHub
• URL: https://github.com/testingautomated-usi/uncertainty-wizard
• Owner: testingautomated-usi
• License: mit
• Created: 2020-12-13T04:33:38.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2023-05-24T21:58:17.000Z (over 1 year ago)
• Last Synced: 2024-10-29T23:30:16.573Z (about 2 months ago)
• Topics: keras, keras-tensorflow, testing, uncertainty, uncertainty-neural-networks, uncertainty-quantification
• Language: Python
• Homepage: https://uncertainty-wizard.readthedocs.io
• Size: 420 KB
• Stars: 44
• Watchers: 5
• Forks: 6
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Citation: CITATION.cff

Awesome Lists containing this project

README

        
![UNCERTAINTY WIZARD](https://github.com/testingautomated-usi/uncertainty-wizard/raw/main/docs/uwiz_logo.PNG)



    

        

    

        

    

        

    

    

        

    

    

        

    

    

        

    

    





    

    

    Best Paper Award at ICST 2021 - Testing Tool Track

    

    



Uncertainty wizard is a plugin on top of `tensorflow.keras`,

 allowing to easily and efficiently create uncertainty-aware deep neural networks:

* Plain Keras Syntax: Use the layers and APIs you know and love.

* Conversion from keras: Convert existing keras models into uncertainty aware models.

* Smart Randomness: Use the same model for point predictions and sampling based inference.

* Fast ensembles: Train and evaluate deep ensembles lazily loaded and using parallel processing - optionally on multiple GPUs.

* Super easy setup: Pip installable. Only tensorflow as dependency.

#### Installation

It's as easy as `pip install uncertainty-wizard`

#### Requirements

`uncertainty-wizard` is tested on python 3.8 and recent tensorflow versions. 

Other versions (python 3.6+ and tensorflow 2.3+) should mostly work as well, but may require some mild tweaks.

#### Documentation

Our documentation is deployed to

[uncertainty-wizard.readthedocs.io](https://uncertainty-wizard.readthedocs.io/).

In addition, as uncertainty wizard has a 100% docstring coverage on public method and classes,

your IDE will be able to provide you with a good amount of docs out of the box.

You may also want to check out the technical tool paper [(preprint)](https://arxiv.org/abs/2101.00982),

describing uncertainty wizard functionality and api as of version `v0.1.0`.

#### Examples

A set of small and easy examples, perfect to get started can be found in the 

[models user guide](https://uncertainty-wizard.readthedocs.io/en/latest/user_guide_models.html)

and the [quantifiers user guide](https://uncertainty-wizard.readthedocs.io/en/latest/user_guide_quantifiers.html).

Larger and examples are also provided - and you can run them in colab right away.

You can find them here: [Jupyter examples](https://uncertainty-wizard.readthedocs.io/en/latest/examples.html).

#### Authors and Papers

Uncertainty wizard was developed by Michael Weiss and Paolo Tonella at USI (Lugano, Switzerland).

If you use it for your research, please cite these papers:

    @inproceedings{Weiss2021FailSafe,  

      title={Fail-safe execution of deep learning based systems through uncertainty monitoring},

      author={Weiss, Michael and Tonella, Paolo},

      booktitle={2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST)},

      pages={24--35},

      year={2021},

      organization={IEEE} 

    }  

    @inproceedings{Weiss2021UncertaintyWizard,  

      title={Uncertainty-wizard: Fast and user-friendly neural network uncertainty quantification},

      author={Weiss, Michael and Tonella, Paolo},

      booktitle={2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST)},

      pages={436--441},

      year={2021},

      organization={IEEE}

    }  

The first paper [(preprint)](https://arxiv.org/abs/2102.00902) provides 

an empricial study comparing the approaches implemented in uncertainty wizard,

and a list of lessons learned useful for reasearchers working with uncertainty wizard.

The second paper [(preprint)](https://arxiv.org/abs/2101.00982) is a technical tool paper,

 providing a more detailed discussion of uncertainty wizards api and implementation.

References to the original work introducing the techniques implemented 

in uncertainty wizard are provided in the papers listed above.

#### Contributing

Issues and PRs are welcome! Before investing a lot of time for a PR, please open an issue first, describing your contribution.

This way, we can make sure that the contribution fits well into this repository.

We also mark issues which are great to start contributing as as [good first issues](https://github.com/testingautomated-usi/uncertainty-wizard/contribute).

If you want to implement an existing issue, don't forget to comment on it s.t. everyone knows that you are working on it.