README.md

metadata

license: apache-2.0
library_name: torch-pointcloud
tags:
  - point-cloud
  - 3d
  - pytorch
  - torch-pointcloud
  - point-mamba
  - classification
datasets:
  - modelnet40
base_model: torch-pointcloud/point-mamba-base.pretrain.dingkang-liang
model-index:
  - name: point-mamba-base.modelnet40.dingkang-liang
    results:
      - task:
          type: point-cloud-classification
        dataset:
          name: ModelNet40
          type: modelnet40
        metrics:
          - name: OA
            type: accuracy
            value: 93.64

Model card for point-mamba-base.modelnet40.dingkang-liang

A PointMamba point cloud classification model (state space model over serialized points). Trained on ModelNet40.

Model Details

• Model Type: Point cloud classification
• Model Stats:
  • Params (M): 12.3
  • Classes: 40
  • Features: 384
• Dataset: ModelNet40
• Metrics: OA 93.64 (reference 93.6)
• Paper: PointMamba: A Simple State Space Model for Point Cloud Analysis
• Converted from: LMD0311/PointMamba (Apache-2.0)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs mamba-ssm, which needs a build matching your torch and CUDA: see the installation guide.

Usage

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

model, info = tp.create_model(
    "point-mamba-base.modelnet40.dingkang-liang",
    task="classification",
    pretrained=True,
    return_info=True,
)
model = model.cuda().eval()  # GPU-only kernels

# 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])
data = {key: value.cuda() for key, value in data.items()}

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

Feature extraction

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, 384)

Citation

@inproceedings{liang2024pointmamba,
  title   = {PointMamba: A Simple State Space Model for Point Cloud Analysis},
  author  = {Dingkang Liang and Xin Zhou and Wei Xu and Xingkui Zhu and Zhikang Zou and Xiaoqing Ye and Xiao Tan and Xiang Bai},
  booktitle = {NeurIPS},
  year    = {2024}
}

@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},
}