help

[bili1bili]

thanks your code. and i have some confusion of this code. in this paper, student(target) and teacher(target) have different augmentation, dropout and noise parameters. but i think there are the same setting both student and teacher in the code.

[Britefury]

The critical lines are:

• line 431; the call to the map method of the data source. This invokes the augment function on each mini-batch.
• line 230; the augment function takes the source and target domain samples, within which on line 232 the code X_tgt_stu, X_tgt_tea = tgt_aug.augment_pair(X_tgt) augments the target sample twice, with different random parameters; once for the student and once for the teacher.