Pointformer

Pointformer copied to clipboard

Why is the result tested with pretrained model is nearly zero?

MSunDYY

# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...

vansin

When can you release the code on KITTI dataset?

2

When can you release the code on KITTI dataset?

jlqzzz

output_features = F.max_pool2d(transformed_feats, kernel_size=[1, ns]) # (B, C, npoint) 在论文当中，关于LocalTransformer作者提到是针对每个local region进行maxpool操作。 这样一来，关于上面这行代码，不应该改为output_features = F.max_pool2d(transformed_feats, kernel_size=[**1, np**])吗？前面的维度变换代码也需要有相应的更改呢？如有错误，烦请批评指正，十分感谢！

Camellia-hz

作者，您好，请问你能开源一下PointRCNN的改进代码嘛？方便我们做对比实验，引用该论文，期待您的回复！

liuhuaijjin

Request of Code and Training Logs on nuScenes Dataset

2

Hi! Dear Pointformer Authors from Gao Huang's lab, Congratulations that your paper has been published on CVPR21. It is a very inspiring work for me! It is also cheering that...

yuhuan-wu

when can you release the code for outdoor datasets?

1

DanielZ98

LinformerEncoder Layer: No Linearisation?

1

Hello, Sorry if this is a silly question, but looking at your code in ptr_base.py line 90 the LinformerEncoder layer doesn't seem to be implementing linear attention at all; what...

JBKnights

Can't get reported preformance based on the latest mmdetection3d

2

Hi, Thanks for your excellent work! I add your code into the latest mmdetection3d repo, but I could not get a similar result as you reported in the paper. I...

xiaobaishu0097

I didn't see the corresponding code for the coordinate refinement part mentioned in the paper. Could you please point out where it is, thanks.

zhiyozhao