Adam J. Stewart

`torchgeo.datamodules.utils.dataset_split` was removed in #2005. My suggestion is to replace all `*_split_pct` parameters with a single `split_lengths` parameter that gets passed to `torch.utils.data.random_split`. We can also rename `length` to `sampler_length`...

I agree that we should have a way to access a nodata mask. However, I'm not sure the best way to do this. Your approach would work, but if you...

> Parsing the nodata mask from the image during training strikes me as breaking the abstractions of the dataloader and the Trainer. I would expect the dataloader to do all...

I also noticed this here: https://github.com/microsoft/torchgeo/pull/1368#issuecomment-1565705950 @calebrob6 can you look into this?

Any luck @calebrob6?

Before #476, we basically had this functionality for most of our `GeoDatasets` already. `RasterDataset.plot` would normalize all images to the 2% to 98% range using `self.rgb_bands` and `self.all_bands`, and would...

Yes, #1407 is likely going to be the limiting factor here. I think the first step is to figure out how to keep things like CRS and transform in the...

Starting a work-in-progress list so that multiple people don't contact the same person. ### Datasets #### In-progress | Source | License | Reason | | --- | --- | ---...

From email conversations, OSCD and HRSCD both have CCA licenses which freely allow redistribution. ReforesTree may require permission from the authors. They have a shared data agreement with WWF. They...

Hugging Face has a maximum individual file size of 50 GB 😢