关于MSDeformAttn中sampling_locations的归一化如何理解问题

[20231211]

elif reference_points.shape[-1] == 4:
sampling_locations = reference_points[:, :, None, :, None, :2]
+ sampling_offsets / self.n_points * reference_points[:, :, None, :, None, 2:] * 0.5
这里归一化为什么是除以 self.n_points * reference_points[:, :, None, :, None, 2:] * 0.5

[long2double]

同问，很是困惑，你知道为什么了么