dsgibbons / shap

A game theoretic approach to explain the output of any machine learning model.
https://shap-community.readthedocs.io/en/latest/
MIT License
25 stars 5 forks source link

fix: use full backward hook for compatibility with torch >= 1.8.0 #94

Closed dsgibbons closed 1 year ago

dsgibbons commented 1 year ago

Port of #1927

dsgibbons commented 1 year ago

Something not happy here. I'll investigate.

dsgibbons commented 1 year ago

This is not worth figuring out here now that we have access to slundberg/shap. Closing.