Using Adam with learning rate decay 0.3 for every 50 epochs, train for 200 epochs; data augmentation follows [this repo](https://github.com/yanx27/Pointnet_Pointnet2_pytorch). For Hengshuang and Nico, initial LR is 1e-3 (I would appreciate if someone could fine-tune these hyper-paramters); for Menghao, initial LR is 1e-4, as suggested by the [author](https://github.com/MenghaoGuo). ModelNet40 classification results (instance average) are listed below:
