cdpierse / transformers-interpret

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Apache License 2.0
1.27k stars 96 forks source link

Output probability - SequenceClassificationExplainer #128

Open SShah30-hue opened 1 year ago

SShah30-hue commented 1 year ago

Hi,

Firstly many thanks for this outstanding work.

My question is simple yet I have not been able to find an answer to it myself. So the way we print multiclass_explainer.predicted_class_name or multiclass_explainer.predicted_class_index, is it possible to print its probability too like multiclass_explainer.predicted_probability ?

I see it is shown in visualize() under "Predicted Label" column in parentheses. I have looked at the source code and it seems there is no functionality that allows that or did I miss something?