shap
ENH: how does pytorch network model use shap.DeepExplainer()
Problem Description
the model is wideDeep,and my code as:
the problem is: AssertionError: The SHAP explanations do not sum up to the model's output! This is either because of a rounding error or because an operator in your computation graph was not fully supported. If the sum difference of %f is significant compared to the scale of your model outputs, please post as a github issue, with a reproducible example so we can debug it. Used framework: pytorch - Max. diff: 0.8651237874997961 - Tolerance: 0.01
Alternative Solutions
No response
Additional Context
No response
Feature request checklist
- [x] I have checked the issue tracker for duplicate issues.
- [ ] I'd be interested in making a PR to implement this feature
You might find your answer here: https://github.com/shap/shap/issues/3263
You should not rely on your shap-outputs as long as you get this error.
The most likely issue is that your model contains an unsupported layer. Did you encounter any warnings that might hint that?
