The overall directory structure should be:
│ACT/
├──cfgs/
├──data/
│ ├──ModelNet/
│ ├──ModelNetFewshot/
│ ├──ScanObjectNN/
│ ├──ShapeNet55-34/
│ ├──shapenetcore_partanno_segmentation_benchmark_v0_normal/
│ ├──Stanford3dDataset_v1.2_Aligned_Version/
│ ├──s3dis/
├──datasets/
├──.......│ModelNet/
├──modelnet40_normal_resampled/
│ ├── modelnet40_shape_names.txt
│ ├── modelnet40_train.txt
│ ├── modelnet40_test.txt
│ ├── modelnet40_train_8192pts_fps.dat
│ ├── modelnet40_test_8192pts_fps.dat- Download: The data can be downloaded from Point-BERT, or from the official website and processed by yourself.
│ModelNetFewshot/
├──5way10shot/
│ ├── 0.pkl
│ ├── ...
│ ├── 9.pkl
├──5way20shot/
│ ├── ...
├──10way10shot/
│ ├── ...
├──10way20shot/
│ ├── ...- Download: The data can be downloaded from Point-BERT. We use the same data split as theirs.
│ScanObjectNN/
├──main_split/
│ ├── training_objectdataset_augmentedrot_scale75.h5
│ ├── test_objectdataset_augmentedrot_scale75.h5
│ ├── training_objectdataset.h5
│ ├── test_objectdataset.h5
├──main_split_nobg/
│ ├── training_objectdataset.h5
│ ├── test_objectdataset.h5- Download: The data can be downloaded from official website.
│ShapeNet55-34/
├──shapenet_pc_masksurf_with_normal/
│ ├── 02691156-1a04e3eab45ca15dd86060f189eb133.npy
│ ├── 02691156-1a6ad7a24bb89733f412783097373bdc.npy
│ ├── .......
├──ShapeNet-55/
│ ├── train.txt
│ └── test.txt- Download: The data can be downloaded from Point-BERT. We use the same data split as theirs.
|shapenetcore_partanno_segmentation_benchmark_v0_normal/
├──02691156/
│ ├── 1a04e3eab45ca15dd86060f189eb133.txt
│ ├── .......
│── .......
│──train_test_split/
│──synsetoffset2category.txt- Download: The data can be downloaded from official website.
|Stanford3dDataset_v1.2_Aligned_Version/
├──Area_1/
│ ├── conferenceRoom_1
│ ├── .......
│── .......
│stanford_indoor3d
│──Area_1_conferenceRoom_1.npy
│──Area_1_office_19.npyPlease prepare the dataset following PointNet:
download the Stanford3dDataset_v1.2_Aligned_Version from here, and get the processed stanford_indoor3d with:
cd data_utils
python collect_indoor3d_data.py