Closed agniv-the-marker closed 1 week ago
Check the docs and the argument for tf.keras.regualizers.l1/l2 is of the form l1/l2 instead of just l in the current version. Without it this breaks:
tf.keras.regualizers.l1/l2
l1
l2
l
net = dde.maps.PFNN( network, "swish", "Glorot normal", regularization=["l2", 1e-8] )
Specifically it gives you the error:
TypeError: L1.__init__() got an unexpected keyword argument 'l'
As of right now, the following works instead:
net = dde.maps.PFNN( network, "swish", "Glorot normal", regularization=["l1+l2", 1e-8, 1e-8] )
But merging would allow for each one to be used on their own.
Split the regularization and model save into two PRs.
TF Regularization
Check the docs and the argument for
tf.keras.regualizers.l1/l2
is of the forml1
/l2
instead of justl
in the current version. Without it this breaks:Specifically it gives you the error:
As of right now, the following works instead:
But merging would allow for each one to be used on their own.