dmlc--dgl
Quan (Andy) Gan
dc19cd5687
* initial commit * second commit * another commit * change docstring * migrating to dgl.nn * fixes * docs * lint * multiple fixes * doc
667 B
667 B
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