Problems encountered in the training process

[Ruangq]

When I changed the use_farthest_point in the configuration file to true, the training time was very long. It took about 3 seconds to train a scene before it was changed, and it took about 180 seconds to train a scene after it was changed. I also monitored the usage of gpu and found that it was basically useless.

[MartinSmeyer]

Yes, this was an experiment and it is like the docu says:

contact_graspnet/contact_graspnet/data.py

Line 67 in f28013a

use_farthest_point {bool} -- use farthest point for downsampling (slow and suspectible to outliers) (default: {False})