mrharicot / monodepth

Unsupervised single image depth prediction with CNNs
Other
2.21k stars 628 forks source link

Test - why don't you evaluate the loss function ? #260

Closed LulaSan closed 2 years ago

LulaSan commented 2 years ago

Hi! I was trying the test mode in your code and I figured out that you don't obtain as output the loss function, in order to see if it is the same as the one in training time. I have seen in the paper that you obtain disparity, convert into depth, and compare with GT. Why don't you calculate also the loss function?

Thank you, Luisa