CondVAEModel.forward

CondVAEModel.forward(data: Tuple[torch.Tensor, torch.Tensor]) Dict[str, torch.Tensor][source]

Forward pass of the model.

Parameters:

data (Tuple[torch.Tensor, torch.Tensor]) – A tuple containing input data tensors, where the first element is ‘x’ and the second element is the conditional part ‘y’.

Returns:

Dict[str, torch.Tensor] – A dictionary containing the model’s output tensors. This could include the latent representation ‘z’, the reconstructed ‘y’, and the reconstructed ‘x’.