mypackage.MyPyroModule

class mypackage.MyPyroModule(n_input, n_latent, n_hidden, n_layers)[source]

Skeleton Variational auto-encoder Pyro 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

n_latent : int

Dimensionality of the latent space

n_hidden : int

Number of nodes per hidden layer

n_layers : int

Number of hidden layers used for encoder and decoder NNs

Methods

get_latent(tensors)

guide(x, log_library)

model(x, log_library)