Skip to content
#

deep-explainer

Here is 1 public repository matching this topic...

This script focuses on explaining a pre-trained CNN’s predictions on the MedMNIST dataset using Deep SHAP. Shapley values are computed for each pixel, summed to create a single Shapley score per image, and saved alongside labels in CSV files for interpretability in medical image classification.

  • Updated Dec 18, 2024
  • Python

Add this topic to your repo

To associate your repository with the deep-explainer topic, visit your repo's landing page and select "manage topics."

Learn more