scvi.nn.Encoder#
- class scvi.nn.Encoder(n_input, n_output, n_cat_list=None, n_layers=1, n_hidden=128, dropout_rate=0.1, distribution='normal', var_eps=0.0001, var_activation=None, return_dist=False, **kwargs)[source]#
Bases:
ModuleEncode data of
n_inputdimensions into a latent space ofn_outputdimensions.Uses a fully-connected neural network of
n_hiddenlayers.- Parameters:
- n_input
int The dimensionality of the input (data space)
- n_output
int The dimensionality of the output (latent space)
- n_cat_list
Iterable[int] (default:None) A list containing the number of categories for each category of interest. Each category will be included using a one-hot encoding
- n_layers
int(default:1) The number of fully-connected hidden layers
- n_hidden
int(default:128) The number of nodes per hidden layer
- dropout_rate
float(default:0.1) Dropout rate to apply to each of the hidden layers
- distribution
str(default:'normal') Distribution of z
- var_eps
float(default:0.0001) Minimum value for the variance; used for numerical stability
- var_activation
Callable|None(default:None) Callable used to ensure positivity of the variance. Defaults to
torch.exp().- return_dist
bool(default:False) Directly return the distribution of z instead of its parameters.
- **kwargs
Keyword args for
FCLayers
- n_input
Attributes table#
Methods table#
|
The forward computation for a single sample. |
Attributes#
Methods#
- Encoder.forward(x, *cat_list)[source]#
The forward computation for a single sample.
Encodes the data into latent space using the encoder network
Generates a mean \( q_m \) and variance \( q_v \)
Samples a new value from i.i.d. multivariate normal \( \sim Ne(q_m, \mathbf{I}q_v) \)
- Parameters:
- Returns:
3-tuple of
torch.Tensortensors of shape(n_latent,)for mean and var, and sample