When I was reading the paper, I found that the semantic segmentation section used KPConv's radius method for sampling, but the radius parameter was set in the code but not called. I saw in the models/blocks that although each convolution had a radius parameter, it was not called. May I ask if I was looking for something wrong? I hope you can tell me which file was used to obtain neighborhood points using the specified radius
When I was reading the paper, I found that the semantic segmentation section used KPConv's radius method for sampling, but the radius parameter was set in the code but not called. I saw in the models/blocks that although each convolution had a radius parameter, it was not called. May I ask if I was looking for something wrong? I hope you can tell me which file was used to obtain neighborhood points using the specified radius