-
I am currently facing a few issues:
(1) What is the purpose of pretraining?
(2) In the model section of PointMamba/cfgs/finetune_modelnet.yaml, the parameter NAME:PointMamba, which indicates that th…
-
Hi !
You used the following version of modelnet dataset (it has 10 k points per shape)
https://shapenet.cs.stanford.edu/media/modelnet40_normal_resampled.zip
while pointnet2 has used an other ver…
-
You wrote that the dataset was taken from modelnet right?
So, I downloaded modelnet40 from kaggle, since modelnet is saved in an object file format (.off), i tried using a simple file converter I g…
-
Thanks for making such a great work. Recently, I tried to train RegFormer on ModelNet, ModelLoNet, Kitti, but the results are not so good. For example, I trained on ModelNet with no modifications to t…
-
Hi @gar1t @yangyanli @ruslo @TSchattschneider @sdukaka
I have downloaded the datasets and unzip them, but I can't run the train code on modelnet, shapenetpart, and S3DIS datasets.
srun -p NV100…
-
I am trying to apply SparseConvNet to ModelNet40 dataset (http://modelnet.cs.princeton.edu/ModelNet40.zip).
It seems that there is some memory leakage. After about 60 epochs the memory consumptino gr…
-
* Name of dataset: Princeton ModelNet
* URL of dataset: https://modelnet.cs.princeton.edu/
* License of dataset: Academic research, see website for more details
* Short description of dataset and u…
-
I use './train_val_modelnet.sh -g 0 -x modelnet_x3_l4' to train my own dataset
What should I do if I want to terminate the program?
-
Can I generate .h5 train/test files using modelnet_dataset.py or data_prep_util.py ( in pointnet ) code such as dataset that can be downloaded at http://modelnet.cs.princeton.edu/ModelNet40.zip ??
…
-
Why does the fine-tuning task on ModelNet40 only converge to 90.0? How to reach 94.1, Is there any setting changed in fine-tuning?