When explaining scikit-learn estimators we can pass arguments like vec or vectorized to vectorize raw text into arrays.
What if we added the same support for Keras Grad-CAM explanations (https://github.com/TeamHG-Memex/eli5/pull/325)? For example, we can make tokens take in a vectorizer function, or use keras.preprocessing.text.Tokenizer. doc could then just be a raw string document.
When explaining scikit-learn estimators we can pass arguments like
vecorvectorizedto vectorize raw text into arrays.What if we added the same support for Keras Grad-CAM explanations (https://github.com/TeamHG-Memex/eli5/pull/325)? For example, we can make
tokenstake in a vectorizer function, or usekeras.preprocessing.text.Tokenizer.doccould then just be a raw string document.