dmlc--dgl
Tong He
558673e139
* commit patch * commit patch * pointnet basic * fix data * reorg * reorg * temp status * remove validate set * add partseg data and model * partseg miou * clean up * fix loss * network definition match paper * fix * fix miou * update data format * fix * fix * working pointnet ssg cls * avoid some pytorch bug * fix script * update hyperparams * add msg module * try different dataset * update new dataset info * quick fix to subgraph * fix speed * update training * update * fix bs * update docstring * update * update * remove parallel reduction in fps * switch to kernel fps, training is 30% faster Co-authored-by: Ubuntu <ubuntu@ip-172-31-20-181.us-west-2.compute.internal>
30 行
835 B
Markdown
30 行
835 B
Markdown
PointNet and PointNet++ for Point Cloud Classification
|
|
====
|
|
|
|
This is a reproduction of the papers
|
|
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593).
|
|
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://arxiv.org/abs/1706.02413).
|
|
|
|
# Performance
|
|
|
|
| Model | Dataset | Metric | Score |
|
|
|-----------------|------------|----------|-------|
|
|
| PointNet | ModelNet40 | Accuracy | 89.3 |
|
|
| PointNet | ShapeNet | mIoU | 83.6 |
|
|
| PointNet++(SSG) | ModelNet40 | Accuracy | 93.26 |
|
|
| PointNet++(MSG) | ModelNet40 | Accuracy | 93.26 |
|
|
|
|
# How to Run
|
|
|
|
For point cloud classification, run with
|
|
|
|
```python
|
|
python train_cls.py
|
|
```
|
|
|
|
For point cloud part-segmentation, run with
|
|
|
|
```python
|
|
python train_partseg.py
|
|
```
|