Image examples

These examples explain machine learning models applied to image data. They are all generated from Jupyter notebooks available on GitHub.

Image classification

Examples using shap.explainers.Partition to explain image classifiers.

• Explain an Intermediate Layer of VGG16 on ImageNet
• Explain an Intermediate Layer of VGG16 on ImageNet (PyTorch)
• Front Page DeepExplainer MNIST Example
• Explain ResNet50 on ImageNet multi-class output using SHAP Partition Explainer
• Multi-class ResNet50 on ImageNet (TensorFlow)
• Multi-class ResNet50 on ImageNet (TensorFlow)
• Multi-input Gradient Explainer MNIST Example
• PyTorch Deep Explainer MNIST example

Image captioning

Examples using shap.explainers.Permutation to produce explanations in a model agnostic manner.

• Explaining Image Captioning (Image to Text) using Azure Cognitive Services and Partition Explainer
• Explaining Image Captioning (Image to Text) using Open Source Image Captioning Model and Partition Explainer