Pointnet_Pointnet2_pytorch
Pointnet_Pointnet2_pytorch copied to clipboard
yanx27
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
Hi，yanx27, It really a great project. I want get the sharpness fields in any point clounds，how should I do？
what is data augmentation trick you added? I want to know the classification accuracy without the additional augmentation trick. what is the classification accuracy with pure augmentations which are mentioned...
The paper has introduced the MRG method but I can not find someone who implements it, Do you have to test this method?
when testing, I used the data with more than 10,000 points and set the --num_point = 4028. But the pointnet2_part_seg_msg prediction result gave the prediction around 3200 points. I was...
Is possible to segmenta (part_seg) of a pointcloud loaded from a file, list an .stl of .ply or .off.
```python class get_model(nn.Module): def __init__(self, num_classes, normal_channel=False): super(get_model, self).__init__() ... self.sa1 = PointNetSetAbstractionMsg(512, [0.1, 0.2, 0.4], [32, 64, 128], 3+additional_channel, [[32, 32, 64], [64, 64, 128], [64, 96, 128]]) self.sa2...
The architecture of the network is different from the original when concatenate the features.
Who has met this problem? How to solve it？It only appears in the test data loading. There is no problem in the train data loading
when I trained train_partset.py with the command: python train_partseg.py --multi_gpu="1, 2" --model_name='pointnet2' --batchsize=16 --epoch=130 --step_size=30 --optimizer='Adam' the program will stop at the first iteration of progress bar, and I even...
