SequentialFixedWindowSampler#

class torch_brain.data.sampler.SequentialFixedWindowSampler(*, sampling_intervals, window_length, step=None, drop_short=False)[source]#

Bases: torch.utils.data.sampler.Sampler

Samples fixed-length windows sequentially, always in the same order. The sampling intervals are defined in the sampling_intervals parameter. sampling_intervals is a dictionary where the keys are the session ids and the values are lists of tuples representing the start and end of the intervals from which to sample.

If the length of a sequence is not evenly divisible by the step, the last window will be added with an overlap with the previous window. This is to ensure that the entire sequence is covered.

Parameters:

  • sampling_intervals (Dict[str, List[Tuple[float, float]]]) – Sampling intervals for each session in the dataset.

  • window_length (float) – Length of the window to sample.

  • step (float, optional) – Step size between windows. If None, it defaults to window_length.

  • drop_short (bool, optional) – Whether to drop windows smaller than window_length. Defaults to False.