Adam J. Stewart
Adam J. Stewart
Python has a concept of "entrypoints" that allow you to do something like: ```console $ torchgeo train conf=... ``` and run `train.py`. We should look into incorporating this. We'll also...
This issue is meant to serve as a proposal for how to fix #278. Please try to poke holes in this proposal and find ways in which it won't work,...
### Issue People keep asking me how to restrict a dataset to a specific spatiotemporal region. The answer is to use an `roi`, but this isn't clear from the docs....
### Summary In order to test our datasets, datamodules, and trainers, we created fake test data for all of our datasets. Later, we started adding `data.py` scripts to generate this...
This is a running list of bugs I've noticed in the documentation that need to be fixed. - [x] Sections don't have permalinks - [x] "Open in Colab" button is...
During the `GeoDataset` refactor (#37), all existing `GeoDataset`s were moved to `VisionDataset`. Now that the `GeoDataset` API has settled down, we should attempt to convert many of these `VisionDataset`s that...
OSCD is a change detection dataset. `OSCDDataset.__getitem__` returns an "image" of shape [2 x C x H x W]. Most of our other datasets return images of shape [C x...
During #329, I noticed a lot of issues with our Chesapeake datamodules and how they integrate with BYOLTask and SemanticSegmentationTask. For example: * https://github.com/microsoft/torchgeo/pull/329#pullrequestreview-840627429 * https://github.com/microsoft/torchgeo/pull/329#pullrequestreview-841013077 * https://github.com/microsoft/torchgeo/pull/329#pullrequestreview-841102399 We should...
We should add a `torchgeo.utils` package that provides utilities for common operations, including stitching together patches to create a prediction on an entire tile. This is equivalent to [`torchvision.utils`](https://pytorch.org/vision/stable/utils.html). See...
For any file-based dataset (currently all of our datasets), a directory may contain geospatial files, auxiliary metadata files, compressed files, etc. In order to use this dataset, we need to...