diff --git a/README.md b/README.md index d691a91d08baa8ceea55b7bc1b427e15dca5b86b..4a63fc517c721f65bd6328021339a1da75af0124 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ python train_cls.py 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: | Model | Accuracy | |--|--| -| Hengshuang | 89.6| +| Hengshuang | 91.7 | | Menghao | 92.6 | | Nico | 85.5 |