Xiaoyong Jin

Results 5 comments of Xiaoyong Jin

@abisee Could you please elaborate on the intuition behind this coverage loss? I didn't read code carefully, but according to the paper, this loss acts like a regularization item along...

@dcmaddix The current code passed the local style checks, but failed in PR check. And I cannot add README due to failed type check. ![image](https://user-images.githubusercontent.com/11488166/110697732-9980b980-81a1-11eb-9b19-c58f1be32c29.png)

I found this problem only occurs in multi-GPU training. It's fine to use the same code without --num_gpus>1.

I have the same problem recently. Is there any update on this request?

> @lostella SHAP and/or LIME are python packages to calculate [Shapley values](https://christophm.github.io/interpretable-ml-book/shapley.html) in order to explain the importance of the variables in black-box models. The topic is quite new and...