README.md

---
license: mit
library_name: torch-pointcloud
tags:
- point-cloud
- 3d
- pytorch
- torch-pointcloud
- pointnet2
- classification
datasets:
- modelnet40
model-index:
- name: pointnet2.modelnet40.openpoints
  results:
  - task:
      type: point-cloud-classification
    dataset:
      name: ModelNet40
      type: modelnet40
    metrics:
    - name: OA
      type: accuracy
      value: 91.9
---

# Model card for pointnet2.modelnet40.openpoints

A PointNet++ point cloud classification model (hierarchical set abstraction). Trained on ModelNet40.

## Model Details

- **Model Type:** Point cloud classification
- **Model Stats:**
  - Params (M): 1.5
  - Input channels: 3
  - Classes: 40
  - Features: 1024
- **Dataset:** ModelNet40
- **Metrics:** OA 91.9 (reference 93.0)
- **Paper:** [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://arxiv.org/abs/1706.02413)
- **Converted from:** [guochengqian/PointNeXt](https://github.com/guochengqian/PointNeXt) (MIT)
- **Library:** [torch-pointcloud](https://github.com/arthurdjn/pytorch-pointcloud)

## Install

```bash
pip install torch-pointcloud
```

## Usage

```python
import torch
import torch_pointcloud as tp
from torch_pointcloud.utils.data import collate

model, info = tp.create_model(
    "pointnet2.modelnet40.openpoints",
    task="classification",
    pretrained=True,
    return_info=True,
)
model = model.eval()

# synthetic sample with the keys a dataset provides
num_points = 8192
sample = {
    "pos": torch.randn(num_points, 3),
    "normal": torch.randn(num_points, 3),
}
data = info["transform"](sample)
data = collate([data])

with torch.no_grad():
    logits = model(data.get("x"), data["pos"], data["batch"])
```

## Feature extraction

```python
with torch.no_grad():
    embeddings = model.forward_features(data.get("x"), data["pos"], data["batch"])

model.reset_classifier(num_classes=0)
with torch.no_grad():
    embeddings = model(data.get("x"), data["pos"], data["batch"])  # (B, 1024)
```

## Citation

```bibtex
@inproceedings{qi2017pointnet2,
  title   = {PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space},
  author  = {Charles R. Qi and Li Yi and Hao Su and Leonidas J. Guibas},
  booktitle = {NeurIPS},
  year    = {2017}
}

@inproceedings{wu2015modelnet,
  title   = {3D ShapeNets: A Deep Representation for Volumetric Shapes},
  author  = {Zhirong Wu and Shuran Song and Aditya Khosla and Fisher Yu and Linguang Zhang and Xiaoou Tang and Jianxiong Xiao},
  booktitle = {CVPR},
  year    = {2015}
}

@software{dujardin2026pytorchpointcloud,
  author  = {Arthur Dujardin},
  title   = {PyTorch PointCloud},
  year    = {2026},
  doi     = {10.5281/zenodo.22159632},
  url     = {https://github.com/arthurdjn/pytorch-pointcloud},
}
```