Attention_mask(calls My in paper) is not used as input of discriminator

[laoliu97]

Hello, I'm very interested in your work.
After reading the v1 paper and code, I found that there is no attention_mask(My) and composite_images (calls Gy in paper)are put into D together, but only the composite_images Gy(Gy=RyMy+x(1-My)) were put into D.
Have you deleted this part of the code？
The following figure is the relevant formula in the paper, but it is not shows in the code.

[laoliu97]

I found that the code only had D_B and D_A,But there is no D_ YA and D_ YB in it.