alibi
alibi copied to clipboard
SeldonIO
Algorithms for explaining machine learning models
Bumps [tj-actions/changed-files](https://github.com/tj-actions/changed-files) from 1.1.2 to 41.0.0. Release notes Sourced from tj-actions/changed-files's releases. v41.0.0 π₯ π₯ BREAKING CHANGE π₯ π₯ A new safe_output input is now available to prevent outputting unsafe...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Hi there! I've seen https://github.com/SeldonIO/alibi/issues/364 in which it's said _"We may extend the types of data handled by the alibi explainers in the future (e.g. working on pandas dataframes) but...
Hi, After calling explain method to get the anchors, I wonder how to use the anchors to predict the label of the explained instance? Is there any function to return...
This is to fix the gradients which could have none values. There are scenarios that some of the inputs have not impact to the target value, IG generates None type...
I'm trying to use KernelShap, but it comes to an error loop. When I fit dataset with torch.tensor type, it shows `TypeError: Type is not supported for background data!` but...
Hello! I found an AI-Specific Code smell in your project. The smell is called: Columns and DataType Not Explicitly Set You can find more information about it in this paper:...
Dear Team, I get the following error when trying to initialise the CEM explainer: # TypeError cem = CEM( lr, mode, (...) clip=0.5, ) cem.fit(X_train, no_info_type='median') --> explanation = cem.explain(X,...
Hi Team, I get the following error when trying to initialise the CEM explainer: `--------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) Input In [52], in () 2 shape = (1,)...
## Issue When the `KernelShap` explainer is configured with `link='logit'`, and the `predictor` returns probabilities of `0` or `1`, the `logit` link function raises errors due to `logit(0) = -inf`...
Hi Team, I am able to use and pass parameters to AnchorImage explain method like below in my jupyter notebook: ```python explanation = explainer.explain(image, threshold=.7, p_sample=.5, tau=0.25, batch_size = 10,...
