PointAugment
PointAugment copied to clipboard
liruihui
Code for PointAugment: an Auto-Augmentation Framework for Point Cloud Classification, CVPR 2020 (Oral)
When i run code, RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 6 and 4 in dimension 0 at /opt/conda/conda-bld/pytorch_1565272279342/work/aten/src/THC/generic/THCTensorMath.cu:71
Hello, when I run this code I get the following error: "NameError: name 'cls_pc_raw' is not defined". I'm not sure if it helps but here is the entire debug message....
Hi! Could you please give some directions - after training the model on ModelNet40 dataset, how can I use Augmentor to produce augmented point clounds from my custom point cloud?
Hello, when I run your code, I encountered the following problems when calculating the loss of classifier: "RuntimeError: one of the variables needed for gradient computation has been modified by...
Hello,liruihui.Thank you for you contribution! I find in your article, you split into two parts.One part is update the classifier, the other one is update augmentor.Is the reason why you...
In your code ```python raw_pt = pt[:,:3,:].contiguous() normal = pt[:,3:,:].transpose(1, 2).contiguous() if C > 3 else None ``` Therefore, I was wondering do you used the normal feature except xyz...
@liruihui Hello, I found this problem in the process of running the code. Do you know why? I hope you can give me some suggestions, thank you.
Thank you for your contribution! I hope you would publish the code soon. I enjoyed the simplicity and effectiveness of your paper and wrote a short blog post with a...
It's a nice job which really inspired me a lot. But I have a question need to answer. Well, I can't understand the idea of generating a 3×3 rotation matrix...
