aljkor comments

Repositories
Issues
Comments

Results 2 comments of


                                            aljkor

use inplace=None as default in densenet

Hi, for example if I try using `shap.DeepExplainer` on basic pytorch models (to explain the output of any machine learning model), I get the following error. `Output 0 of BackwardHookFunctionBackward...

use inplace=None as default in densenet

Here I found the same issue with a different model: https://github.com/shap/shap/issues/3466