This is the first notebook in series of exploring OpenVINO™ Explainable AI (XAI):
- OpenVINO™ Explainable AI Toolkit (1/3): Basic
- OpenVINO™ Explainable AI Toolkit (2/3): Deep Dive
- OpenVINO™ Explainable AI Toolkit (3/3): Saliency map interpretation
It will show the first steps in the XAI toolkit, covering the following topics:
- Explanation of XAI toolkit and concept of saliency maps.
- How to create saliency map for OpenVINO™ IR models using XAI.
A saliency map is a visualization technique that highlights regions of the interest in an image from the model perspective. For example, it can be used to explain classification model predictions for a particular label. Here is an example of a saliency map that you will get in this notebook:
This is a self-contained example that relies solely on its own code.
We recommend running the notebook in a virtual environment. You only need a Jupyter server to start.
For details, please refer to Installation Guide.
