TobiasMascetta

Dimensionality, Potential-based sampling, input spheres and batch_neighbors in Classification

5

Hi Hugues, first of all, thank you for releasing the PyTorch Version of your code and especially for the link to your PhD thesis in one of the other issues....

generic_logsumexp with larger point clouds

2

Hi jeanfeydy, I have one question regarding a strange error that occurs when using default geomloss.SampleLoss() with larger point clouds (>= 25k points): For smaller point clouds (~2500) everything works...

Hello Hugues, From what I understand from your thesis and the code, an input normalization strategy (for example unit sphere normalization) is not necessary because of the grid-based input subsampling...

Point Cloud Density and V-RAM OOM

1

Hi Hugues, I have one further question about the flexibility of your model and its V-RAM usage. [Question] I am encountering heavily varying V-RAM usage and even mid-training OOM on...