Skip to content

Conversation

@vl-dud
Copy link
Contributor

@vl-dud vl-dud commented Oct 22, 2025

Enable dropout_rate for Pytorch in the same way as the TF1 backend:

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]
    },
)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant