You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi @MiguelMonteiro, @K-Rilla, I re-checked the issue and found that norm can accept a tuple as input that contains the parameters needed by the matching norm layer.
You can do something like this:
from monai.networks.nets.densenet import DenseNet121
model = DenseNet121(spatial_dims=3, in_channels=1, out_channels=2048, norm=("layer", {"normalized_shape": [c, h, d]}))
Convert it to discussion, feel free to create another issue if meet further issue. Thanks.
Describe the bug
Layer norm does not work with densenet, returns the following error when instantiating model:
To Reproduce
Expected behavior
It should work or not be an option.
Environment
Python 3.10, pytorch 2.0.1, monai 1.3.0
Additional context
Bug has previously been reported here Project-MONAI/research-contributions#196
The text was updated successfully, but these errors were encountered: