sccross.models.layers.ZILNDataDecoder.forward

ZILNDataDecoder.forward(u, b, l)

Decode data from sample and feature latent

Parameters

• u (Tensor) – Sample latent

• v – Feature latent

• b (Tensor) – Batch index

• l (Optional[Tensor]) – Optional normalizer

Return type

ZILN

Returns

recon – Data reconstruction distribution