rnaglib.dataset_transforms.get_loader

rnaglib.dataset_transforms.get_loader(dataset, batch_size=5, num_workers=0, split=True, split_train=0.7, split_valid=0.85, verbose=False, persistent_workers=True)[source]

Fetch a loader object for a given dataset.

Parameters:

  • dataset – RNADataset for loading

  • batch_size – Number of items in batch

  • num_workers – Number of worker processes for data loading

  • split – Whether to compute train/val/test splits

  • split_train – Proportion of dataset to keep for training (default 0.7)

  • split_valid – Proportion of dataset to keep for validation (default 0.85)

  • verbose – Print updates during loading

  • persistent_workers – Keep workers alive between epochs

Returns:

If split=False: single DataLoader. If split=True: tuple of (train_loader, valid_loader, test_loader)