Hi has anyone been able to train LRA-Net on their own custom dataset? If so, which categories and how well did it perform? Which part of the code needs to be modified? I want to train it to do completion of dense pointclouds of individual trees. Do you think it will work well and how many trees will I need? Can I train it from scratch or will I need to use transfer learning?
Thank you for your interest. I am not sure our work might perform well on completion of trees, because they are to some extent "unstructured". However, I think the following work: GRNet or TopNet might be more suitable to your case.
wuhang100
commented
3 years ago
Hi has anyone been able to train LRA-Net on their own custom dataset? If so, which categories and how well did it perform? Which part of the code needs to be modified? I want to train it to do completion of dense pointclouds of individual trees. Do you think it will work well and how many trees will I need? Can I train it from scratch or will I need to use transfer learning?