Tensorflow 1.x backend: layer-by-layer dropout rate setting for DeepONet

[vl-dud]

Now you can set dropout_rate more flexibly:

net = dde.nn.DeepONet(
    [10, 128, 128, 128],
    [dim_x, 128, 128, 128],
    "tanh",
    "Glorot normal",
    dropout_rate={
        "branch": [0.5, 0.3],
        "trunk": [0.5, 0.3, 0.2]
    },
)

[lululxvi]

There are a lot of code like this

if isinstance(self.dropout_rate_branch, list):

To simplify the code, you can convert the single dropout to a list as well. Then in the code, there is no need to use if to check.

[vl-dud]

Fixed