Hello, everyone. I would like to ask if I can create neural network models with multiple inputs and mixed data inputs by DEEPXDE.
the next is a demo of deepxde (Inverse problem for the Poisson equation with unknown forcing field):
""""
Next, we choose the networks. We use two networks, one to train for u(x) and the other to train for q(x). Here, we use two fully connected neural networks of depth 4 (i.e., 3 hidden layers) and width 20.
Hello, everyone. I would like to ask if I can create neural network models with multiple inputs and mixed data inputs by DEEPXDE.
the next is a demo of deepxde (Inverse problem for the Poisson equation with unknown forcing field):
"""" Next, we choose the networks. We use two networks, one to train for u(x) and the other to train for q(x). Here, we use two fully connected neural networks of depth 4 (i.e., 3 hidden layers) and width 20.
net = dde.nn.PFNN([1, [20, 20], [20, 20], [20, 20], 2], "tanh", "Glorot uniform")
""""
like the above demo, can i realize my idea by seting 1 to 2 ?