Forward function with multiple outputs?

Question

Typically the forward function in nn.module of pytorch computes and returns predictions for inputs happening in the forward pass. Sometimes though, intermediate computations might be useful to return. For example, for an encoder, one might need to return both the encoding and reconstruction in the forward pass to be used later in the loss.

Question: Can Pytorch's nn.Module's forward function, return multiple outputs? Eg a tuple of outputs consisting predictions and intermediate values?
Does such a return value not mess up the backward propagation or autograd? If it does, how would you handle cases where multiple functions of input are incorporated in the loss function?

(The question should be valid in tensorflow too.)

Answer 1

"The question should be valid in Tensorflow too", but PyTorch and Tensorflow are different frameworks. I can answer for PyTorch at least.

Yes you can return a tuple containing any final and or intermediate result. And this does not mess up back propagation since the graph is saved implicitly from the tensors outputs using callbacks and cached tensors.