Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Songqing Zhang 15ace31a16 | 1 month ago | |
---|---|---|
.. | ||
ModelNetDataLoader.py | 1 year ago | |
README.md | 2 years ago | |
ShapeNet.py | 1 month ago | |
helper.py | 1 year ago | |
pct.py | 1 year ago | |
provider.py | 1 year ago | |
train_cls.py | 1 year ago | |
train_partseg.py | 1 year ago |
This is a reproduction of the paper: PCT: Point cloud transformer.
Task | Dataset | Metric | Score - Paper | Score - DGL (Adam) | Time(s) - DGL |
---|---|---|---|---|---|
Classification | ModelNet40 | Accuracy | 93.2 | 92.1 | 740.0 |
Part Segmentation | ShapeNet | mIoU | 86.4 | 85.6 | 390.0 |
During training, a random translation in [−0.2, 0.2], a random anisotropic scaling in [0.67, 1.5] and a random input dropout were applied to augment the input data.
For point cloud classification, run with
python train_cls.py
For point cloud part-segmentation, run with
python train_partseg.py
No Description
Python C++ Jupyter Notebook Cuda Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》