scvi.inference Package

Functions

load_posterior(dir_path, model[, use_cuda])

Function to use in order to retrieve a posterior that was saved using the save_posterior method

Classes

Trainer(model, gene_dataset[, use_cuda, …])

The abstract Trainer class for training a PyTorch model and monitoring its statistics.

Posterior(model, gene_dataset[, shuffle, …])

The functional data unit.

UnsupervisedTrainer(model, gene_dataset[, …])

Class for unsupervised training of an autoencoder.

AdapterTrainer(model, gene_dataset, …[, …])

JointSemiSupervisedTrainer(model, …)

SemiSupervisedTrainer(model, gene_dataset[, …])

Class for the semi-supervised training of an autoencoder.

AlternateSemiSupervisedTrainer(*args, **kwargs)

ClassifierTrainer(*args[, train_size, …])

Class for training a classifier either on the raw data or on top of the latent space of another model.

JVAETrainer(model, discriminator, …[, …])

The trainer class for the unsupervised training of JVAE.

TotalPosterior(model, gene_dataset[, …])

The functional data unit for totalVI.

TotalTrainer(model, dataset[, train_size, …])

Unsupervised training for totalVI using variational inference