mypackage.MyModel¶

class mypackage.MyModel(adata, n_hidden=128, n_latent=10, n_layers=1, **model_kwargs)[source]¶

Skeleton for an scvi-tools model.

Please use this skeleton to create new models.

Parameters

adata : AnnDataAnnData: AnnData object that has been registered via setup_anndata().
n_hidden : intint (default: 128): Number of nodes per hidden layer.
n_latent : intint (default: 10): Dimensionality of the latent space.
n_layers : intint (default: 1): Number of hidden layers used for encoder and decoder NNs.
**model_kwargs: Keyword args for MyModule

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> scvi.data.setup_anndata(adata, batch_key="batch")
>>> vae = mypackage.MyModel(adata)
>>> vae.train()
>>> adata.obsm["X_mymodel"] = vae.get_latent_representation()

Attributes

`device`
`history`	Returns computed metrics during training.
`is_trained`
`test_indices`
`train_indices`
`validation_indices`

Methods

`get_elbo`([adata, indices, batch_size])	Return the ELBO for the data.
`get_latent_representation`([adata, indices, …])	Return the latent representation for each cell.
`get_marginal_ll`([adata, indices, …])	Return the marginal LL for the data.
`get_reconstruction_error`([adata, indices, …])	Return the reconstruction error for the data.
`load`(dir_path[, adata, use_gpu])	Instantiate a model from the saved output.
`save`(dir_path[, overwrite, save_anndata])	Save the state of the model.
`to_device`(device)	Move model to device.
`train`([max_epochs, use_gpu, train_size, …])	Train the model.