Closed ajuric closed 5 years ago
I found out the problem.
Number 180 is not divisible with 24 - the elevation angle has range set to 180: https://github.com/YoungXIAO13/PoseFromShape/blob/master/training.py#L124
So the solution is to set these two numbers (range and number of classes) to be divisible.
Anyway, pytorch error should have been more informative ...
Thanks for your notice, I've made a new commit to change all xxx_classes as a function of bin_size which is used to define the classification bin size for all Euler angles, where you only need to change the bin_size to conduct an ablation study.
When trying different number of classes (bins) for angles, I get
The error happens inside the
DeltaLoss
class in thedelta_loss
method in the line:(link to line: https://github.com/YoungXIAO13/PoseFromShape/blob/master/auxiliary/loss.py#L29)
I tried debugging, but wasn't successful. I mostly use TF, so maybe I'm missing something very common in Pytorch?
When I use default number of classes (azimuth=24, elevation=12, in-plane=24), training runs normally and completes.