How to launch code with PointNetVlad model? about logg3d-net HOT 2 CLOSED

Hi,
You should be able to train PointNetVLAD using the following command:
torchpack dist-run -np ${_NGPU} python training/train.py --train_pipeline 'PointNetVLAD' --point_loss_weight 0
by setting the dataset parameter either KittiTupleDataset or MulRanTupleDataset . The point_loss_weight parameter is set to zero as PointNetVLAD only uses the global loss during training.
Additionally, you can set the following parameters to the values used in the PointNetVLAD paper: lazy_loss, ignore_zero_loss, positives_per_query, negatives_per_query, loss_margin_1, loss_margin_2.

After training, you can generate results using the same evaluation commands given in the readme by providing the additional parameter --eval_pipeline 'PointNetVLAD' and setting --checkpoint_name to the path of the pretrained weights.

from logg3d-net.

Also, make sure to use the --pnv_preprocessing 'True' parameter for PointNetVLAD.

from logg3d-net.