hyperparmeters and gpus.

[zeqri]

Hi,

in train.sh the configuration sets ns, nv, max radius and batch_size to 16, 4, 5 and 2, but in the args file in the checkpoint folder for the best model provided these parameters are set to different values. to replicate the results should I stick with these values or the ones in the args file in checkpoint folder? what is exactly the number of gpus that were used in training?

thank you in advance.

[onlyonewater]

so, does anyone know the hype-parameters or reproduce the results successfully?