hanjianghu / dasgil Goto Github PK

Hi, I would like to have some explanations about the seg. loss. I noticed that in your paper you wrote 'Similar to the image forward propagation for depth reconstruction, we apply score regression and the softmax layer for the outputs at multiple layers of generator Gs'.
Instead, analyzing your code in backward_G function of model.py, the seg loss seems to be applied just on the last output of Gs (lines 271-273), differently from the depth loss which is applied to all outputs from the 5th layer of Gd as reported in the paper.
Am I missing something?
Thanks

How do I test it on a single image query?

In the process of running the train.py, the triplet loss will be 0， is it normal?