Pointnet_Pointnet2_pytorch icon indicating copy to clipboard operation
Pointnet_Pointnet2_pytorch copied to clipboard

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Results 166 Pointnet_Pointnet2_pytorch issues
Sort by recently updated
recently updated
newest added

Can this model be quantized in pytorch, and is there any relevant quantization code?

![Screenshot 2024-10-14 161459](https://github.com/user-attachments/assets/71395e55-c92d-4a4e-9332-5a8b3e2cd2cd) when I train my own dataset (point clouds of bridges and roads), it takes 15h for just one epoch. How can I improve my model? Which parameters...

I cannot access the stanford website for the ModelNet40 dataset, so i found one on kaggle and use it instead. However, the train process would stick on load dataset phase...

问题在于 pointnet2_utils 模块中的 球形领域查询函数:query_ball_point,其存在严重 BUG!! 完整代码如下: def query_ball_point(radius, nsample, xyz, new_xyz): """ Input: radius: local region radius nsample: max sample number in local region xyz: all points, [B, N, 3]...

First, thank you for sharing this excellent work! I have a question regarding the data splitting strategy and performance benchmarking: I noticed that Area 5 is designated as the test...

hello, I try to visit https://[shapenet.cs.stanford.edu](https://shapenet.cs.stanford.edu/media/modelnet40_normal_resampled.zip)/media/modelnet40_normal_resampled.zip,but false

Hi yanx27, I hope you're doing well! I’m currently working on a project involving ​PointNet for 3D point cloud classification, and I noticed your repository has been incredibly helpful. Would...

According to the provided log for part_seg_msg, the model got 90 accurancy at the first epoch. But I cannot reach 90 even after 100 epoch. Does it make sense???? ![Image](https://github.com/user-attachments/assets/38e37aa2-0f93-43ea-93da-151d505b7561)

hello,i want to use the part-segment model on my own datasets,i just want the classifier give me the prediction of each point but i dont have the label of my...

First, thank you for your project; it's really helpful. I tried to restart training from the last checkpoint, but it never happened. And it starts from scratch Please can you...