use a list of output layer in the PFNN

[enigne]

Discussed in https://github.com/lululxvi/deepxde/discussions/1627

^{Originally posted by enigne January 17, 2024} Hi,

I'm currently using deepxde to do ice sheet modeling , TensorFlow2 backend. I would like to ask if it is possible to make deepxde.nn.PFNN to be able to handle output layers defined by a list, instead of by an integer. For example, deepxde.nn.PFNN([2, [20,20,20], [20,20,20], [2,2,1]],"tanh", "Glorot uniform") which is a parallel net with 2 inputs, and 5 (in total) outputs, but clustered into 2,2,1. In this case, we will get 3 parallel nets, but 5 different output.

[tsarikahin]

I guess you have to create your custom network, this is not supported.

[praksharma]

No it is not. But if you have a code you can modify it. But what is Parallel nets, is it XPINN, CPINN or something else?