https://github.com/hcmlab/alterfactuals
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.5%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: hcmlab
- Language: Python
- Default Branch: main
- Size: 3.37 MB
Statistics
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
This is the code for our IJCAI 2024 paper: 'Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifiers' The paper, including the appendix, can directly be accessed through this repository.
Install all required libraries listed in requirements.txt
Depending on what you want to train, navigate to the corresponding directory. E.g. if you want to train a classifier, head to /countercounter/classifier. To traina GAN, set your config in countercounter/gan/execution/configs and run /countercounter/gan/execution/execute.
To train another type of model: The folder structure is pretty much the same for all models. Some have an explicity training.py file. If this exists, use this to train.
Owner
- Name: Human Centered Artifical Intelligence
- Login: hcmlab
- Kind: organization
- Location: Augsburg, Germany
- Website: www.hcai.eu
- Repositories: 29
- Profile: https://github.com/hcmlab
Human Centered Artifical Intelligence Lab of the Augsburg University
GitHub Events
Total
Last Year
Dependencies
- joblib ==0.17.0
- lime ==0.2.0.1
- matplotlib ==3.4.1
- numpy ==1.19.2
- pandas ==1.1.3
- pillow ==8.0.1
- piqa ==1.1.0
- pyyaml ==5.4.1
- scikit-image ==0.17.2
- scikit-learn ==0.23.2
- scipy ==1.5.2
- seaborn ==0.11.1
- shap ==0.39.0
- statsmodels ==0.12.2
- tensorboard ==2.3.0
- torch ==1.8.0
- torchvision ==0.9.0
- yaml *