Fixed check of input shapes when dealing with multiple inputs.

marcoancona / DeepExplain

A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)

https://arxiv.org/abs/1711.06104

MIT License

720 stars 133 forks source link

Fixed check of input shapes when dealing with multiple inputs. #49

Closed schulter closed 4 years ago

schulter commented 4 years ago

Hi, I fixed the issue #48 for multiple inputs and adapted the error messages to be a little more concise.