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
In code, we use l1 loss to regress only the masked regions, and use ae loss to regress the unmasked regions. This simply means l1 + ae = ae loss of entire image. The paper's description is correct.
@wuyxiquanquan this is the auto-encoder loss (as in BEGANs). The l1 loss regresses the holes (masked regions) to the ground truth regions. The ae loss is the standard auto-encoder loss to reconstruct the rest of the image. Note that the Generator loss is l1 + ae, as described above.
In your paper, I can only find the l1 loss, I am confused about the ae loss?
The text was updated successfully, but these errors were encountered: