Closed HarshitGupta29 closed 10 months ago
There are no particular tricks. Is the problem that transforming the input and using our function runs out of memory? Could you use an inplace operation to transform it?
I implemented it and the code is available here: https://github.com/HarshitGupta29/3D-Chamfer-Loss-with-Mahalanobis-Distance
Discussed in https://github.com/facebookresearch/pytorch3d/discussions/1684