mypackage.MyModule

class mypackage.MyModule(n_input, library_log_means, library_log_vars, n_batch=0, n_hidden=128, n_latent=10, n_layers=1, dropout_rate=0.1)

Skeleton Variational auto-encoder model.

Here we implement a basic version of scVI’s underlying VAE [Lopez18]. This implementation is for instructional purposes only.

Parameters

n_input : int

Number of input genes

library_log_means : ndarray

1 x n_batch array of means of the log library sizes. Parameterizes prior on library size if not using observed library size.

library_log_vars : ndarray

1 x n_batch array of variances of the log library sizes. Parameterizes prior on library size if not using observed library size.

n_batch : int (default: 0)

Number of batches, if 0, no batch correction is performed.

n_hidden : int (default: 128)

Number of nodes per hidden layer

n_latent : int (default: 10)

Dimensionality of the latent space

n_layers : int (default: 1)

Number of hidden layers used for encoder and decoder NNs

dropout_rate : float (default: 0.1)

Dropout rate for neural networks

Methods

generative(z, library)	Runs the generative model.
inference(x)	High level inference method.
loss(tensors, inference_outputs, ...[, ...])	Compute the loss for a minibatch of data.
marginal_ll(tensors, n_mc_samples)
sample(tensors[, n_samples, library_size])	Generate observation samples from the posterior predictive distribution.