Training and test splits

[lhoangan]

Hi,

I'm wondering if you could release the file ids in the training and test split being used in the paper? It's only said that "The ORR dataset contains 8,862 samples, which are split into 7,071 for training and 1,791 for testing, without geographic overlapping". I can't seem to find such information.

There seems to be also a small discrepancy with the information provided in the ORR's dataset, so the file ids would be needed to pick the correct training and test split.

(Raw) Navtech CTS350-X Radar Frames: 8867

(Processed) Navtech CTS350-X Radar Optimised SE2 Odometry Frames: 8865

Thanks