thetis
Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines) for uncertainty consistency (calibration), fairness, and other safety-relevant aspects.
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (19.7%) to scientific vocabulary
Keywords
Repository
Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines) for uncertainty consistency (calibration), fairness, and other safety-relevant aspects.
Basic Info
- Host: GitHub
- Owner: EFS-OpenSource
- License: other
- Language: Python
- Default Branch: main
- Homepage: https://thetis.de
- Size: 1.04 MB
Statistics
- Stars: 5
- Watchers: 0
- Forks: 1
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
Even if your AI is as strong as Achilles, Thetis will certainly know about its weaknesses.
Checkout our new online dashboard for Thetis and register for free!
Thetis is our comprehensive solution for AI system analysis, ensuring that AI applications remain safe, reliable, and ethical. Designed with regulatory requirements like the AI Act of the European Union in mind, Thetis provides detailed findings and analytics, offering key insights to support your auditing and QA processes.
Thetis evaluates various aspects of AI systems, including performance, uncertainty consistency (calibration), fairness, and robustness. It also assesses the quality of your datasets, alerting you to potential hidden issues. Thetis supports a wide range of AI tasks, such as detection, classification, and regression.
This repository and README serve as a technical user guide for engineers. If you are a legal professional or a compliance officer, visit our product page (in German) or directly try out Thetis online to discover how Thetis can enhance the safety, reliability, and ethical standards of your AI applications.
For detailed documentation and technical background on all analysis modes and features, visit the API Documentation Page.
Installation
As a python package, Thetis is installed from the Python Package Index (PyPI) using Python's installer pip. Within your python environment, simply type:
shell
$ pip install thetis
This will install the latest available version of Thetis and all its dependencies.
Usage and obtaining a license
The core functions of Thetis are free to use. If you wish to conduct deeper investigations of your AI application, you can easily apply for a license. Send us a mail and we will reach out to you soon!
The usage examples in this repository come with free demo licenses tied to each example. These examples demonstrate the full functionalities of Thetis.
Thetis will automatically detect your license file if it is placed in your working directory or at the following locations:
- Windows:
<User>\\AppData\\Local\\Thetis\\license.dat - Unix:
~/.local/thetis/license.dat
Alternatively, you can specify the license location as a parameter when calling Thetis.
Quickstart
We have prepared several examples to demonstrate Thetis's capabilities and help you get started with your own model data analysis. Depending on your use case, refer to the following examples:
Get in touch
If you have any questions, would like to schedule a personal demo, or wish to provide feedback, please contact us via mail at thetis@efs-techhub.com.
Terms of Use
The terms of use of Thetis can be found at https://app.thetis.de/static/terms. A detailed description of our packages and system requirements can be found at https://app.thetis.de/download/Leistungsbeschreibung.pdf (in German).
Owner
- Name: e:fs Techhub
- Login: EFS-OpenSource
- Kind: organization
- Website: https://efs-techhub.com
- Repositories: 3
- Profile: https://github.com/EFS-OpenSource
Always learning
Citation (CITATION.cff)
cff-version: 1.2.0
title: Thetis AI System Analysis Toolbox
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Fabian
family-names: Küppers
email: fabian.kueppers@efs-techhub.com
affiliation: 'e:fs TechHub GmbH'
orcid: 'https://orcid.org/0009-0005-9856-7527'
- given-names: Jonas
family-names: Schneider
email: jonas.schneider@efs-techhub.com
affiliation: 'e:fs TechHub GmbH'
- given-names: Thorsten
family-names: Gedicke
email: thorsten.gedicke@efs-techhub.com
affiliation: 'e:fs TechHub GmbH'
repository-code: 'https://github.com/EFS-OpenSource/Thetis'
url: 'https://thetis.de'
abstract: >-
Solution for AI system analysis regarding performance,
uncertainty consistency (calibration), fairness, and other
aspects relevant for regulatory compliance.
keywords:
- ai
- machine learning
- deep learning
- fairness
- uncertainty calibration
- confidence calibration
- robustness
- explainability
- data quality
- neural networks
- validation
GitHub Events
Total
- Release event: 2
- Watch event: 2
- Member event: 1
- Push event: 7
- Create event: 2
Last Year
- Release event: 2
- Watch event: 2
- Member event: 1
- Push event: 7
- Create event: 2
Committers
Last synced: about 2 years ago
Top Committers
| Name | Commits | |
|---|---|---|
| Fabian Kueppers | f****s@e****m | 27 |
| Fabian Küppers | g****b@f****e | 5 |
| Kueppers, Fabian Dr. (EFS-GT1) | F****s@e****m | 2 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 0
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: about 5 hours
- Total issue authors: 0
- Total pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
- fabiankueppers (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
-
Total downloads:
- pypi 256 last-month
- Total docker downloads: 18
-
Total dependent packages: 1
(may contain duplicates) -
Total dependent repositories: 0
(may contain duplicates) - Total versions: 19
- Total maintainers: 1
pypi.org: thetis
Solution for AI system analysis regarding performance, uncertainty consistency (calibration), fairness, and other aspects relevant for regulatory compliance.
- Homepage: https://thetis.de
- Documentation: https://efs-opensource.github.io/Thetis
- License: Proprietary
-
Latest release: 0.2.4
published 6 months ago
Rankings
Maintainers (1)
pypi.org: thetiscore
Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines) for uncertainty consistency (calibration), fairness, and other safety-relevant aspects.
- Homepage: https://thetis.de
- Documentation: https://efs-opensource.github.io/Thetis
- License: other
-
Latest release: 0.2.4
published 6 months ago