Bilal Alsallakh

Thank you very much @JohannesK14 for the initiative! An LRP tutorial is indeed due. How about your submit a PR of your tutorial (ideally as a Jupyter notebook) under https://github.com/pytorch/captum/tree/master/tutorials?...

Hi @soloccc, In order to better help you, we need to look into your source code. Could you share snippets showing how you define your model (including the forward function),...

Hi @soloccc , apologies for the missing to respond earlier! You might be facing the same issue as in #445. Can you make sure both the forward function and `autograd`...

Thank you for the good proposal, @soupault! Would you like to create a PR with your solution (along with a test case)? We can then review it and make sure...

Hi @y12uc231 , Currently the [LIME tutorial](https://captum.ai/tutorials/Image_and_Text_Classification_LIME) focuses on image and text models. However, LIME is definitely applicable to tabular data. The [following tutorial](https://captum.ai/tutorials/Titanic_Basic_Interpret) performs attribution for tabular data (the...

Hi @ybzhaoplus, thank you for commenting on the implementation! The current implementation should correctly index the H and W dimensions, because an input tensor is first converted into a tuple:...

Thanks for the clarification, @ybzhaoplus. We are interested in understanding this issue further. Do you mind sharing a Colab notebook illustrating the exception and the warning you got? Thanks!

Hi @Arvind-Ideas2IT , it seems that Captum Insights (as a React.js app) was not built properly? Running `BUILD_INSIGHTS=true python setup.py install` as proposed in https://github.com/pytorch/captum/issues/628#issuecomment-797081799 should help. Let me know...

Hi @elixir-code , Captum's [LayerIntegratedGradients](https://captum.ai/api/layer.html#layer-integrated-gradients) implementation allows you to define a custom baseline if a zero vector does not fit your problem (see `baselines` in the arguments to the `.attribute()`...

Hi @PascalHbr , this article might inspire you in applying suited methods for video: https://link.springer.com/article/10.1007/s11263-019-01225-w Hope this helps