dmlc--dgl
Hongzhi (Steve), Chen
704bcaf6dd
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-63.ap-northeast-1.compute.internal>
Dynamic EdgeConv
This is a reproduction of the paper Dynamic Graph CNN for Learning on Point Clouds.
The reproduced experiment is the 40-class classification on the ModelNet40 dataset. The sampled point clouds are identical to that of PointNet.
To train and test the model, simply run
python main.py
The model currently takes 3 minutes to train an epoch on Tesla V100, and an additional 17 seconds to run a validation and 20 seconds to run a test.
The best validation performance is 93.5% with a test performance of 91.8%.
Dependencies
h5pytqdm