captum 0.7.0
torch 2.3.0
torchtext 0.18.0
spacy 3.7.6
i’d like to be able to replicate the results in this captum tutorial, but can’t figure out how to get the vocabulary associated with the pre-trained CNN’s embedding for use by spacy on test sentences?
interpret_sentence() makes critical use of the legacy TEXT.vocab.stoi() and Label.vocab.itos() dropped by torchtext version >= 0.9?
this has been a captum issue for two years?!