Closed gaosanyuan closed 2 years ago
reprojection_losses.append(self.compute_reprojection_loss(pred, target))
identity_reprojection_losses.append(
self.compute_reprojection_loss(pred, target))
combined = torch.cat((identity_reprojection_loss, reprojection_loss), dim=1)
to_optimise, idxs = torch.min(combined, dim=1)
I have read the code, but I still didn't know how the auto masking work in the code. I only found the mask is computed here:
if not self.opt.disable_automasking: outputs["identity_selection/{}".format(scale)] = ( idxs > identity_reprojection_loss.shape[1] - 1).float()
But, I don't know where it works.
Can anyone explain it for me, thanks