README.md

---
license: mit
library_name: torch-pointcloud
tags:
- point-cloud
- 3d
- pytorch
- torch-pointcloud
- pointgpt
- classification
datasets:
- scanobjectnn
base_model: torch-pointcloud/pointgpt-b.pretrain.guangyan-chen
model-index:
- name: pointgpt-b.scanobjectnn-objonly.guangyan-chen
  results:
  - task:
      type: point-cloud-classification
    dataset:
      name: ScanObjectNN (OBJ_ONLY)
      type: scanobjectnn
    metrics:
    - name: OA
      type: accuracy
      value: 95.18
---

# Model card for pointgpt-b.scanobjectnn-objonly.guangyan-chen

A PointGPT point cloud classification model (autoregressive generative pretraining transformer). Trained on ScanObjectNN (OBJ_ONLY).

## Model Details

- **Model Type:** Point cloud classification
- **Model Stats:**
  - Params (M): 120.4
  - Classes: 15
  - Features: 1536
- **Dataset:** ScanObjectNN (OBJ_ONLY)
- **Metrics:** OA 95.18 (reference 95.2)
- **Paper:** [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://arxiv.org/abs/2305.11487)
- **Converted from:** [CGuangyan-BIT/PointGPT](https://github.com/CGuangyan-BIT/PointGPT) (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(
    "pointgpt-b.scanobjectnn-objonly.guangyan-chen",
    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),
}
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, 1536)
```

## Citation

```bibtex
@inproceedings{chen2023pointgpt,
  title   = {PointGPT: Auto-regressively Generative Pre-training from Point Clouds},
  author  = {Guangyan Chen and Meiling Wang and Yi Yang and Kai Yu and Li Yuan and Yufeng Yue},
  booktitle = {NeurIPS},
  year    = {2023}
}

@inproceedings{uy2019scanobjectnn,
  title   = {Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data},
  author  = {Mikaela Angelina Uy and Quang-Hieu Pham and Binh-Son Hua and Duc Thanh Nguyen and Sai-Kit Yeung},
  booktitle = {ICCV},
  year    = {2019}
}

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