Why is the output of 'predict_normalE2' set to 2？

[DUTMultiMediaLab]

Thank you for releasing the code. I have a question about generating dense depth.
In 'depthCompletionNew_block' and 'depthCompletionNew_blockN' functions, the final output is generated by 'predict_normalE2'.
However, depth map is usually a 1-channel map, the output of 'predict_normalE2' is 2 channels.
What's the theory for this?
Thank you very much!

def predict_normalE2(in_planes):
return nn.Conv2d(in_planes, 2, kernel_size=1, stride=1, padding=0, bias=True)