You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
After training, we need get out the embedding vectors, look the code inside and out, I guess I could use below method, please confirm whether it is right or is there any right approach?
As we are using label encoding, also want to confirm the list_vector match the sequence of index of lbe.classes_, for example, list_vector[0] is the embedding vector of lbe.classes_ first key(label), after LabelEncoder fit_transform()
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
After training, we need get out the embedding vectors, look the code inside and out, I guess I could use below method, please confirm whether it is right or is there any right approach?
list_vector = model.embedding_dict[''].weight.data
As we are using label encoding, also want to confirm the list_vector match the sequence of index of lbe.classes_, for example, list_vector[0] is the embedding vector of lbe.classes_ first key(label), after LabelEncoder fit_transform()
Thanks a lot!
Beta Was this translation helpful? Give feedback.
All reactions