Pointnet_Pointnet2_pytorch
Pointnet_Pointnet2_pytorch copied to clipboard
yanx27
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
See [https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/151](https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/151)
Hi. I am working on a custom dataset. I finally trained the model. I am wondering how to write inference code for new unlabeled data. Can someone help?
Among them, intensify represents the intensity of the point cloud reflected by the lidar. How do I need to change the network structure to make the input like this
Hi!I have one question.How to get the forecast result of part_seg? This result contains all the input points and their label, not just the sampling points.Look forward to your reply!
Two questions about the visualiztion part. 1. `pc_utils.py` can not run properly. Base on the code, the reason is `load_data` function is not defined in `ShapeNetDataLoader.py`. 2. what is the...
RuntimeError: shape '[-1, 2064, 1]' is invalid for input of size 4098 channel = 3 normal=false
Hi, thanks for your amazing work. I used your code on my customized dataset, which I down sampled using voxelization with voxel size of 0.05. In the function query_ball_points it...
In part segmentation, since the data is normalized during training, the size of the pre result is different from that of the actual data. How can I recover it?
