About CUDA kernel error and some questions.

[Deleted user]

Hello, thank you for providing the code.
I just started learning about pointcloud and there are a few things I don't understand.

(1). What is the role of embedding layer in PointMLP?
(2). Which part is the Geometric Affine Module in code? Also, in Figure 6 of the paper, how many times the Geometric Affine Module appeared?
(3). Do you learn all features in one process with the entire point cloud as input, or n selected point features?

That's all I ask. Thank you very much.

[ma-xu]

Hi @popopochan
Thanks for your interests, here are the responses.

1. just mapping 3-d xyz to high dimensional features.
2. See the LocalGrouper module in our codes. 4 times, each stage has one.
3. Sry that I didn't get it. We feed all the 1024 points into the network for feature extraction (classification task).

Feel free to let mw know if you have any further questions.

[Deleted user]

Hi, @ma-xu
Thank you for your timely reply.
I still have some questions.

1. I understand that this module mapping in a low dimension to high dimension, but what is the reason (purpose) for embedding?
2. I understand. Is this the affine module before the preblock at all stage?
3. It's a neighborhood-by-neighbour process, but at the end it’s extracting all the features collectively?

Thank you.

[ma-xu]

1. Directly operating on 3-dimensional features may not achieve good performance.
2. Yes.
3. If I correctly understand your question (operating locally in each stage), the answer is yes.

[Deleted user]

OK, thank you.