How does one deal with the RunTimeError when the dimension have been counted a lot and can't infer the dimensions?

1

What does the error:

RuntimeError: already counted a million dimensions in a given sequence. Most likely your items are also sequences and there's no way to infer how many dimension should the tensor have

mean and how does one fix it?

I only have:

W = Variable(w_init, requires_grad=True)
W_avg = Variable(torch.FloatTensor(W).type(dtype), requires_grad=False)

but I hope to make this hope more generally helpful beyond just my very (probably newbie) question.

2

Please post your full code and the full error stack to know which one of both lines of code
gives the error.
Where do you declare and initialize “w_init” ?