scvi.dataloaders.AnnDataLoader#
- class scvi.dataloaders.AnnDataLoader(adata_manager, shuffle=False, indices=None, batch_size=128, data_and_attributes=None, drop_last=False, iter_ndarray=False, **data_loader_kwargs)[source]#
DataLoader for loading tensors from AnnData objects.
- Parameters:
adata_manager (
AnnDataManager
) –AnnDataManager
object with a registered AnnData object.shuffle (default:
False
) – Whether the data should be shuffledindices (default:
None
) – The indices of the observations in the adata to loadbatch_size (Optional[int]) – minibatch size to load each iteration
data_and_attributes (
Optional
[dict
] (default:None
)) – Dictionary with keys representing keys in data registry (adata_manager.data_registry
) and value equal to desired numpy loading type (later made into torch tensor). IfNone
, defaults to all registered data.data_loader_kwargs – Keyword arguments for
DataLoader
iter_ndarray (
bool
(default:False
)) – Whether to iterate over numpy arrays instead of torch tensors
Attributes table#
Methods table#
Attributes#
multiprocessing_context
dataset
- AnnDataLoader.dataset: Dataset[T_co]#
batch_size
- AnnDataLoader.batch_size: Optional[int]#
num_workers
- AnnDataLoader.num_workers: int#
pin_memory
- AnnDataLoader.pin_memory: bool#
drop_last
- AnnDataLoader.drop_last: bool#
timeout
- AnnDataLoader.timeout: float#
sampler
- AnnDataLoader.sampler: Union[Sampler, Iterable]#
pin_memory_device
- AnnDataLoader.pin_memory_device: str#
prefetch_factor
- AnnDataLoader.prefetch_factor: int#
Methods#
check_worker_number_rationality