A question

[cvchanghao]

I use torch.jit.trace() and save my own CNN_model. The return of my network is a tuple contains 3 tensors.
When I use C++ as front, I use auto output = module.forward(inputs); to get my result. But how can I get the 3 tensors individually? and do some C++ operations?

Thank you!

[mfl28]

script::module's forward method returns an IValue type that has many methods to convert to other types, see here. You might want to try toTensorList(), toTensorVector() or toTuple().

[mfl28]

Closing this for now, hope I could help you with your problem :)