loss function

[Nd-sole]

Hey,

Can you share the loss function implementation which you use for your paper? I want to reimplement your paper.

[lucaskyle]

i think u may check their previous works
https://github.com/haofanwang/accurate-head-pose

in the paper they mentioned:

A new wrapped-loss stabilizes the network at large yaws.

Yaw prediction is divided into 120 3◦ bins covering the full range of yaws (−180◦,180◦].
Pitch and roll predictions are each made from 66 3◦ bins covering the range [−99◦,99◦], although
only the bins from [−90,90] are ultimately used.

i think they just quite the same.

[Algabri]

@Nd-sole did you find their loss function? I would like to implement it with Pytorch. I did not find it here https://pytorch.org/docs/stable/nn.html#loss-functions