---
license: mit
library_name: torch-pointcloud
tags:
- point-cloud
- 3d
- pytorch
- torch-pointcloud
- dgcnn
- classification
datasets:
- modelnet40
model-index:
- name: dgcnn.modelnet40-2048.an-tao
  results:
  - task:
      type: point-cloud-classification
    dataset:
      name: ModelNet40
      type: modelnet40
    metrics:
    - name: OA
      type: accuracy
      value: 93.6
---

# Model card for dgcnn.modelnet40-2048.an-tao

A DGCNN point cloud classification model (dynamic graph convolution over EdgeConv features). Trained on ModelNet40.

## Model Details

- **Model Type:** Point cloud classification
- **Model Stats:**
  - Params (M): 1.8
  - Classes: 40
  - Features: 2048
- **Dataset:** ModelNet40
- **Metrics:** OA 93.6 (reference 93.6)
- **Paper:** [Dynamic Graph CNN for Learning on Point Clouds](https://arxiv.org/abs/1801.07829)
- **Converted from:** [antao97/dgcnn.pytorch](https://github.com/antao97/dgcnn.pytorch) (MIT)
- **Library:** [torch-pointcloud](https://github.com/arthurdjn/pytorch-pointcloud)

## Install

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

This checkpoint also needs `pyg-lib`, which needs a build matching your torch and CUDA: see the [installation guide](https://pytorch-pointcloud.org/installation/).

## Usage

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

model, info = tp.create_model(
    "dgcnn.modelnet40-2048.an-tao",
    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, 2048)
```

## Citation

```bibtex
@article{wang2019dgcnn,
  title   = {Dynamic Graph CNN for Learning on Point Clouds},
  author  = {Yue Wang and Yongbin Sun and Ziwei Liu and Sanjay E. Sarma and Michael M. Bronstein and Justin M. Solomon},
  journal = {ACM Transactions on Graphics},
  volume  = {38},
  number  = {5},
  year    = {2019}
}

@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},
}
```