Gunner Stone
Gunner Stone
Did this ever get fixed? Still running into same issue
Usually NaN errors occur during model training due to values getting so small they become 0. Dividing by that 0 is no good. My guess is that your model is...
Getting the same error. My dataloader is extracting a single data input as size `[batch_size, num_channels, num_points]` num_channels = 3 # for xyz channels Not sure what rel_pos is or...
I got the same error... Python modules are difficult to code, especially when your file tree looks as web-like as this project's. It also looks like some imported library uses...
Aha I think I have solved the mystery. The authors enable you to train & test the AE separately only in order to prove it works effectively as a Pointnet...
The publication does not specify the number of training iterations required to achieve the reported performance results. This omission complicates direct comparisons between their original method and subsequent improvements. For...