myoverse.datasets.base.WindowedDataset.__init__

WindowedDataset.__init__(zarr_path, split='training', modalities=None, window_size=200, window_stride=None, n_windows=None, seed=None, device=None, dtype=torch.float32, cache_in_ram=True)

Parameters:

• zarr_path (Path | str)

• split (str)

• modalities (Sequence[str] | None)

• window_size (int)

• window_stride (int | None)

• n_windows (int | None)

• seed (int | None)

• device (device | str | None)

• dtype (dtype)

• cache_in_ram (bool)