mauicv

Dear @HeyItsBethany3, Thanks for the question, > Do you have any method for seeing which feature has the most importance/changeability power in a counterfactual? (Which features do more to move...

Hey @MattiaGallegati, Thanks for opening the issue. Can you be more specific, what kind of model are you using and what kind of explainer do you use? Broadly speaking It...

Hey @MattiaGallegati, Why can you not revert the sequence of transformations?

Fitting the explainer on non-processed data requires the model has been trained on the non-processed data. If that's not the case then you have to be able to invert the...

I think the issue is that the CNN you've trained takes input shape `(28, 28, 3)` as per: ```py model.add(Conv2D(16,(3,3),activation='relu',input_shape=(28,28,3))) ``` but then later you take an image, `x_train[0]`, resize...

Dear @krishnakripaj, Thanks for opening the issue. This sounds a lot like [this](https://docs.seldon.io/projects/alibi/en/latest/overview/faq.html#why-is-my-anchor-explanation-empty-tabular-or-text-data-or-black-image-data). What does your dataset look like? How balanced is it?

hmmm, I think it's still likely to be one of: - The predicted class of the data point does not change regardless of the perturbations applied to it. - The...

Hey @krishnakripaj, So I think what's happening is that the algorithm first tries the empty anchor and determines that its precision is greater than the requested precision threshold. This is...

__Note__: Error only arises after reloading the CFRL_Explainer which makes me think that we change the accuracy of the weight in saving or loading.

difference arises first [here](https://github.com/SeldonIO/alibi/blob/7e8b45d41cf8b7bc0dbf52db7ac9c861ebb901fd/alibi/explainers/backends/tensorflow/cfrl_base.py#L318) other notes: 1. Effect only occurs after we load the model. So the pre-saved and post-loaded models are deterministic. 2. Model weights are equal 3. Difference...