Model card for pct.modelnet40.strawberry-eat-mango

A PCT point cloud classification model (offset-attention point cloud transformer). Trained on ModelNet40.

Model Details

• Model Type: Point cloud classification
• Model Stats:
  • Params (M): 2.9
  • Classes: 40
  • Features: 1024
• Dataset: ModelNet40
• Metrics: OA 93.27, mAcc 89.99
• Paper: PCT: Point Cloud Transformer
• Converted from: Strawberry-Eat-Mango/PCT_Pytorch (MIT)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs pyg-lib, 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(
    "pct.modelnet40.strawberry-eat-mango",
    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

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

@article{guo2021pct,
  title   = {PCT: Point Cloud Transformer},
  author  = {Meng-Hao Guo and Jun-Xiong Cai and Zheng-Ning Liu and Tai-Jiang Mu and Ralph R. Martin and Shi-Min Hu},
  journal = {Computational Visual Media},
  volume  = {7},
  number  = {2},
  pages   = {187--199},
  year    = {2021}
}

@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},
}