Inconsistency between paper and code about cag_uda

[Turlan]

And could you release/explain the code for updating CAC between stages? In the released code, there exists a moving-average implementation. Which one did you use?

CAG_UDA/models/adaptation_model.py

Line 529 in b6fbea6

def update_objective_SingleVector(self, id, vector, name='moving_average', ):

[RogerZhangzz]

Hi there,
Thanks for your suggestion.

1. The batch size was set to 1 when I trained the model. Then in my re-implementation, I set it to 4 for a quick convergence. Both settings would be fine for the final performance. Plz note that you have to increase the crop size if you choose to use 1 as the batch size.

2. \ 3. Very thank you for what you have pointed out. I will check it out.

3. I have uploaded the CAC code (cac.py) and modified the instructions.