PCT icon indicating copy to clipboard operation
PCT copied to clipboard

Jittor implementation of PCT:Point Cloud Transformer

Results 22 PCT issues
Sort by recently updated
recently updated
newest added

Thanks for your great job! Here, I still do not understand the steps you mentioned: (1) Choose query point I. (2)Convert the value of attention A[i,j] to the depth of...

i found there haven't any describe about how the local feature embedding layer combine with the SA layer, what is the final PCT architecture like?

Hi, thanks for your wonderful work. And I have some questions about models in /networks/cls/pct.py. 1. Does `Point_Transformer` on 86 line corresponds to a model without neighbor embedding? 2. Does...

Hello, thank you for releasing the code! I was wondering if you could tell me the model size (MB) and the number of parameters for PCT-2L and PCT-3L? Thank you!

Hi, Thanks for releasing the code. Can you release the PCT code for the PartSeg or simply show the parameters of each layer, please? Best

Hi, I want to ask how is positional embedding implemented in the model? xyz = self.pos_xyz(xyz) but there isn't self.pos_xyz given

Hi, thank you for releasing the code! However, I could not find the details of the `CosineAnnealingLR`. Could you tell me how to set `T_max` and other attributes for this...

Dear authors, Thank you for sharing your code and contributions. I would like to use your code in my project, while there is no LICENSE present in your repository. May...

Hello Guo! I found that much more epochs were needed in part_seg task when I replaced the model in Pointnet++ with PCT. (Pointnet++ code from https://github.com/yanx27/Pointnet_Pointnet2_pytorch) Pointnet++ needs less than...

when run pct ```python self.sa1 = SA_Layer(channels) File "/home/ssd/zjl/zjl/point/PointCloudLib/networks/cls/pct.py", line 205, in __init__ self.q_conv.conv.weight = self.k_conv.conv.weight AttributeError: 'Conv1d' object has no attribute 'conv' ```