Adam J. Stewart

@calebrob6 that example is for train-test splitting, not for sampling. We already have [random_grid_cell_assignment](https://torchgeo.readthedocs.io/en/stable/api/datasets.html#torchgeo.datasets.random_grid_cell_assignment) for that use case.

It's still not clear what the purpose or advantage of this sampler is. We already have: * [random_grid_cell_assignment](https://torchgeo.readthedocs.io/en/stable/api/datasets.html#torchgeo.datasets.random_grid_cell_assignment): for creating a train-val-test _split_ based on a checkerboard * [GridGeoSampler](https://torchgeo.readthedocs.io/en/stable/api/samplers.html#grid-geo-sampler): for...

You would need 2 GridGeoSamplers offset by 1 row/col to achieve the same thing. But again, I don't know why you would want to sample in this way unless you...

Thanks for the explanation! Yes, I think `grid_cell_assignment` is the right strategy if you want it to be deterministic instead of random. You should be able to modify the existing...