some a fews problem about compute depth details

[Tony-Hou]

self.depth_channels = int( (self.dbound[1] - self.dbound[0]) / self.dbound[2])

1. why is depth channels setting 'd_bound': [2.0, 58.0, 0.5] to compute channels is 112 ?
2. https://github.com/Megvii-BaseDetection/BEVDepth/blob/main/exps/bev_depth_lss_r50_256x704_128x128_24e.py#L271 Why to multiply 3.0 depth_loss?

[lilkeker]

I don't understand this place very well,too. Why do it to set 3 times the depth_loss, and it seems that this depth_loss only supervises the depth predicted by the key frame. I now want to use the point cloud to complete the predicted depth of the image, but it seems It can only complete the depth predicted by the key frame frame.

[lilkeker]