arthurdjn's picture
Update README.md and config.json and model.safetensors for recon.scanobjectnn-objonly.zekun-qi
e9935d8 verified
|
Raw History Blame Contribute Delete
2.96 kB
---
license: mit
library_name: torch-pointcloud
tags:
- point-cloud
- 3d
- pytorch
- torch-pointcloud
- recon
- classification
datasets:
- scanobjectnn
base_model: torch-pointcloud/recon.pretrain.zekun-qi
model-index:
- name: recon.scanobjectnn-objonly.zekun-qi
results:
- task:
type: point-cloud-classification
dataset:
name: ScanObjectNN (OBJ_ONLY)
type: scanobjectnn
metrics:
- name: OA
type: accuracy
value: 93.63
- name: mAcc
type: accuracy
value: 93.74
---
# Model card for recon.scanobjectnn-objonly.zekun-qi
A ReCon point cloud classification model (masked point transformer with cross-modal contrastive queries). Trained on ScanObjectNN (OBJ_ONLY).
## Model Details
- **Model Type:** Point cloud classification
- **Model Stats:**
- Params (M): 43.6
- Classes: 15
- Features: 1536
- **Dataset:** ScanObjectNN (OBJ_ONLY)
- **Metrics:** OA 93.63, mAcc 93.74
- **Paper:** [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://arxiv.org/abs/2302.02318)
- **Converted from:** [qizekun/ReCon](https://github.com/qizekun/ReCon) (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(
"recon.scanobjectnn-objonly.zekun-qi",
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 = collate([sample])
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{qi2023recon,
title = {Contrast with Reconstruct: Contrastive {3D} Representation Learning Guided by Generative Pretraining},
author = {Qi, Zekun and Dong, Runpei and Fan, Guofan and Ge, Zheng and Zhang, Xiangyu and Ma, Kaisheng and Yi, Li},
booktitle = {ICML},
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},
}
```