Kevin Musgrave

The original OfficeHome dataset has very large images, so I downscaled them so that the shortest side is 256 pixels, but this isn't mentioned anywhere in the docs or the...

It should take in 3 datasets: - source - labeled target - unlabeled target

Right now it's hardcoded to use `src_logits`. Adding a domain parameter (set to either `src` or `target`) would allow CLossHook to be used for supervised domain adaptation as well. https://github.com/KevinMusgrave/pytorch-adapt/blob/3b2713c4860b325c79481f11307a193bb381d53f/src/pytorch_adapt/hooks/classification.py#L75-L88

...to avoid collisions

For example: ```python # return all hooks inside of "classifier" that are of type ATDOCHook hooks = classifier.get_hooks("ATDOCHook") ```

- [x] As hooks - [ ] As adapters

Anytime softmax is applied to "_logits", add "_preds".