Closed sieme97 closed 4 years ago
Hi, in order to properly train the network using the photometric image loss only you should change the activation function of each prediction layer using a sigmoid (as in Monodepth1, Godard et al). Moreover, you should also replace our bilinear sampler function with this one: https://github.com/mrharicot/monodepth/blob/master/bilinear_sampler.py
Alright, thanks
Alright, thanks
Hi, in order to properly train the network using the photometric image loss only you should change the activation function of each prediction layer using a sigmoid (as in Monodepth1, Godard et al). Moreover, you should also replace our bilinear sampler function with this one: https://github.com/mrharicot/monodepth/blob/master/bilinear_sampler.py
I have changed the disparity prediction layer activation function and the bilinear sampler, but the training is still not going well.
Try to disable the "crop" approach by setting 'patch_width' and 'patch_height' to the same size of 'width' and 'height'. Our choice to crop images is well suited for proxies but not for the photometric loss alone.
The issue has been resolved after applying sigmoid actiavation on only disparity refinement layers, and relu on initial disparity layers.
Training from scratch without proxy labels produce very bad results. Why is it so? Do I have to change the max disp value in correlation map?