Give PyTorch Lightning dummy data loaders so it runs the training loop. The ModelWrapper already has the training data from its __init__.

Wraps a dataset so that PyTorch Lightning's validation step can be turned into a visualization step.

A frame sampler picks the frames that should be sampled from a dataset's video. It makes sense to break the logic for frame sampling into an inter

Give a dataclass that bundles tensors, arrays, and lists functionality that mimics regular tensor manipulation. For example, this allows you to sl