Home
ClarityAI is a Python package designed to empower machine learning practitioners with a range of interpretability methods to enhance the transparency and explainability of their CNN models. Currently, ClarityAI can calculate attention and saliency maps.
Prerequisites: Python 3.6 or higher
You can install ClarityAI using pip:
pip install ClarityAI==1.0.0
Once installed, you can import ClarityAI and start using its features:
import clarityaiFor specific examples of how to use ClarityAI's functions, please refer here.
For full documentation on functions and classes, please refer to the attention maps and saliency maps pages.
If you have any questions, please contact us at [email protected]. As well, you can open an issue here.
Version 1.0.0 of ClarityAI was first published in August 2023.
ClarityAI is designed to help users quickly integrate interpretability methods into their personal projects. However, ClarityAI is just a tool meant to help users - not replace users' own judgments on interpretability and ethical use cases of their ML models.
Please also note that ClarityAI is a package created for fun/educational purposes! There exist several popular interpretability libraries available in the Python ecosystem, which are much better designed and maintained, such as SHAP, LIME, Yellowbrick, and InterpretML.