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
@LiuJinxue The value of negative_label will change in negative_label = np.random.choice(label_index_map.keys())
it is used to avoid the situation that only one label in a batch.
what does "negative_label = anchor_label" mean? Is it correct?
The text was updated successfully, but these errors were encountered: