BUG: image_plot Original image NOT showing

[snkrbhr]

Issue Description

I simply follow this example from the official website Explain ResNet50 ImageNet classification using Partition explainer but the output image is partial.

Example: https://shap.readthedocs.io/en/latest/example_notebooks/image_examples/image_classification/Image%20Multi%20Class.html

When using the shap.image_plot(shap_value) function to visualize SHAP (SHapley Additive exPlanations) values for an original image, the original images are not displayed as expected. The shap_value parameter represents the SHAP values associated with the image, and the function is designed to display the original image alongside its SHAP values. However, in the current implementation, the original image is not appearing in the generated plot.

This issue persist in Jupyter notebook, Colab and even I tried Chrom and Firefox browser

Minimal Reproducible Example

shap.image_plot(shap_value)

Follow this Example: https://shap.readthedocs.io/en/latest/example_notebooks/image_examples/image_classification/Image%20Multi%20Class.html

Traceback

No response

Expected Behavior

The shap.image_plot function is expected to display the original image along with the SHAP values to provide a comprehensive visualization of feature attributions. This helps users understand the impact of each feature on the model's output.

Bug report checklist

• I have checked that this issue has not already been reported.
• I have confirmed this bug exists on the latest release of shap.
• I have confirmed this bug exists on the master branch of shap.
• I'd be interested in making a PR to fix this bug

Installed Versions

0.43.0

[igraugar]

I have the same problem, following.

[caminada87]

Try to transform the original image in the second argument of image_plot: "pixel_values (numpy.array)" like this (i just use one image here so [0:1]):

shap.image_plot(shap_values, X[0:1]/255)