Replies: 1 comment
-
|
There is no decay in DeepXDE. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I want to achieve the loss weight as the training process goes down.This is my code:
model.complie('adam', lr=0.001, loss_weights=[1,10000], external_trainable_variables=C)
I hope 10000 to linearly decay to 1 when the trainning is over.
Thanks for your help!
Beta Was this translation helpful? Give feedback.
All reactions