Best way to handle variable number of inputs

Hi everyone,

I am currently implementing a PyTorch Model, that has to deal with a varying number of inputs, i.e. it can be initialized to handle for example 3 or 6 input tensors. I am currently trying to figure out what is the best way to implement this. I thought of using a dictionary in my forward method.

def forward(self, mydict):
     pass

Does anyone of you have another idea to handle this?

Thank you very much!

Why not use *args and **kwargs?