load_posterior

scvi.inference.load_posterior(dir_path, model, use_cuda='auto', **posterior_kwargs)[source]

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

Because of pytorch model loading usage, this function needs a scVI model object initialized with exact same parameters that during training. Because saved posteriors correspond to already trained models, data is loaded sequentially using a SequentialSampler.

Parameters

  • dir_path (strstr) – directory containing the posterior properties to be retrieved.

  • model (ModuleModule) – scVI initialized model.

  • use_cuda (str, bool, NoneUnion[str, bool, None]) – Specifies if the computations should be perfomed with a GPU. Default: True If auto, then cuda availability is inferred, with a preference to load on GPU. If False, the model will be loaded on the CPU, even if it was trained using a GPU.

  • **posterior_kwargs – additional parameters to feed to the posterior constructor.

Returns

>>> model = VAE(nb_genes, n_batches, n_hidden=128, n_latent=10)
>>> trainer = UnsupervisedTrainer(vae, dataset, train_size=0.5, use_cuda=use_cuda)
>>> trainer.train(n_epochs=200)
>>> trainer.train_set.save_posterior("./my_run_train_posterior")

>>> model = VAE(nb_genes, n_batches, n_hidden=128, n_latent=10)
>>> post = load_posterior("./my_run_train_posterior", model=model)