dgcnn.pytorch
dgcnn.pytorch copied to clipboard
Why the implemented network architecture is different with the architecture in the paper?
Hello! I have noticed a discrepancy between the network architecture used in the implemented code and the architecture described in the original paper. Below, you can see a figure depicting the architecture of the class DGCNN_semseg_s3dis, as plotted by me. Do I make any mistakes, or if the implemented code deviates from the architecture outlined in the original paper?
I follow the original TensorFlow code in here. The architecture in this repo is the same as the original code.