PointNet can't predict segmentation on created dataset

[reptinias]

Hello everybody

I'm currently working on my bachelor project and I'm using the PointNet deep neural network.
My project group and I have created a dataset of point clouds, but we can't train PointNet to predict segmentation with the dataset.
When we run the benchmark dataset, the system runs and can predict segmentation, so we know that the error is in the dataset somewhere, even though we have tried our best to have our dataset look like the original benchmark dataset.

These are the thing we have tried:

1. We have tried downsampling the point clouds
2. We have tried downscaling so all values are between 0 and 1
3. We have tried run an euclidean clustering function on the data
4. We have tried replicate another dataset, which was created using the same raw data

In the attached link, images of the datafiles with a description can be found.

Kind regards