scvi.dataloaders.ConcatDataLoader#
- class scvi.dataloaders.ConcatDataLoader(adata_manager, indices_list, shuffle=False, batch_size=128, data_and_attributes=None, drop_last=False, **data_loader_kwargs)[source]#
DataLoader that supports a list of list of indices to load.
- Parameters:
adata_manager (
AnnDataManager
) –AnnDataManager
object that has been created viasetup_anndata
.indices_list (
List
[List
[int
]]) – List where each element is a list of indices in the adata to loadshuffle (
bool
(default:False
)) – Whether the data should be shuffledbatch_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
Attributes table#
Methods table#
Attributes#
multiprocessing_context
dataset
- ConcatDataLoader.dataset: Dataset[T_co]#
batch_size
- ConcatDataLoader.batch_size: Optional[int]#
num_workers
- ConcatDataLoader.num_workers: int#
pin_memory
- ConcatDataLoader.pin_memory: bool#
drop_last
- ConcatDataLoader.drop_last: bool#
timeout
- ConcatDataLoader.timeout: float#
sampler
- ConcatDataLoader.sampler: Union[Sampler, Iterable]#
pin_memory_device
- ConcatDataLoader.pin_memory_device: str#
prefetch_factor
- ConcatDataLoader.prefetch_factor: int#
Methods#
check_worker_number_rationality