Why initial "self.layers" twice in vectornet.py?

[Joe12138]

Thanks for your excellent work. I have some questions about the code.

1. In vectornet.py, why initial self.layers twice in NewSubGraph class ?
2. In lib.py, why does not use self.key directly in the forward function of GlobalGRaph class ?

[GentleSmile]

1. The first initialization of self.layers can be removed as it is covered by the second initialization
2. linear(hidden_states, self.key.weight) indicates not use the bias of linear layer self.key.