scvi.core.data_loaders.AnnotationDataLoader

class scvi.core.data_loaders.AnnotationDataLoader(*args, model_zl=False, **kwargs)[source]

Attributes

indices

Returns the current dataloader indices used by the object.

n_cells

Returns the number of studied cells.

scvi_data_loader_type

Returns the dataloader class name.

Methods

accuracy()

compute_predictions([soft])

param soft

(Default value = False)

elbo()

Returns the Evidence Lower Bound associated to the object.

hierarchical_accuracy()

marginal_ll([n_mc_samples])

Estimates the marginal likelihood of the object’s data.

nn_latentspace(data_loader)

reconstruction_error()

Returns the reconstruction error associated to the object.

sequential([batch_size])

Returns a copy of the object that iterate over the data sequentially.

to_cuda(tensors)

Converts dict of tensors to cuda.

unsupervised_classification_accuracy()

update(data_loader_kwargs)

Updates the dataloader.

update_batch_size(batch_size)

update_sampler_indices(idx)

Updates the data loader indices.