Replies: 2 comments
-
Hi, can we implement the feature using a hook to warm up the loss weight? |
Beta Was this translation helpful? Give feedback.
0 replies
-
yup sure, but how can we implement without modifying the current |
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
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I would like to use
param_scheduler
on loss_weight, in some algorithms, we may want to ramp up the loss weight until the certain value. but in the current implementations, we can only passoptimi_wrapper
toparam_scheduler
. So it would be better to generlize that.Any idea?
Beta Was this translation helpful? Give feedback.
All reactions