Confuse about predict scales and shifts and the loss

[Liupengshuaige]

Hi：
In another issue, you said the inverseForm outputs 4 values which stand for scales and shifts, so if I want to minimize the inverseForm loss, the scales should be close to 1 and shifts should be chose to 0.But in your code, the loss is (((distance_coeffs*distance_coeffs).sum(dim=1))**0.5).mean(), which will push all of 4 values to 0, why ?
Looking forward to your reply. Thank you!

[sborse3]

Hey @Liupengshuaige, thanks for the question! For Euclidean, we normalize the parameters before training IF network, as this will reduce bias towards any one parameter