GACNet icon indicating copy to clipboard operation
GACNet copied to clipboard

Pytorch implementation of 'Graph Attention Convolution for Point Cloud Segmentation'

Results 13 GACNet issues
Sort by recently updated
recently updated
newest added

KeyError: "Unable to open object (object 'data' doesn't exist)" ![image](https://user-images.githubusercontent.com/52451124/143735506-aa0abb97-2d8d-4769-9a23-916410c63ac3.png) How to solve this problem?

Hi Yan, Thank you for your fantastic work. Your model runs perfectly on my personal desktop. I am just wondering would you mind if you could publish a Tensorflow-version code...

Hi Yan, Thank you for your fantastic work. But I have some questions. I found that 'batchnorm' and 'DROPOUT' were used extensively in the code. I implemented the model 40...

why I encounter overfitting problem? I used Area5 as the test dataset , after about 4 epoches, the test loss begin increasing obviously, the train loss looked well. I changed...

Hi! Appreciate your implement work, I have a training question to ask. The default number of epoches in your code is 200, but it is too long for my GPU...

https://github.com/yanx27/GACNet/blob/1dbc79d3e65a3df0686fb139d88bce0a0d4a7be9/model.py#L177

wget: /home/ouc/anaconda2/lib/libuuid.so.1: no version information available (required by wget) --2020-07-21 19:25:46-- https://shapenet.cs.stanford.edu/media/indoor3d_sem_seg_hdf5_data.zip Resolving shapenet.cs.stanford.edu (shapenet.cs.stanford.edu)... 171.67.77.19 Connecting to shapenet.cs.stanford.edu (shapenet.cs.stanford.edu)|171.67.77.19|:443... connected. ERROR: cannot verify shapenet.cs.stanford.edu's certificate, issued by ‘CN=InCommon RSA...

Hi, @yanx27 , Thanks for releasing such useful package. As mentioned in the original paper, another dataset Semantic3D is also evaluated. Would you provide the dataloader code for Semantic3D dataset...

Thank you very much for sharing the fantastic code! I wondered about the data format of the function`square_distance` in the `model.py` script when I was reading it. Could you please...