bogdan-kulynych / textfool

Plausible looking adversarial examples for text classification
MIT License
92 stars 32 forks source link

in data_utils, the token.rank is 0 #3

Open Eleanor456 opened 5 years ago

Eleanor456 commented 5 years ago

In the data_utils.py, all the token.rank in function extract_features is 0. Hence, X_train and X_test are the same which are the vector as [1, 1, 1, 1....., 0, 0]. What is the problem?