keras ReduceLROnPlateau callback expects lr property
Opened this issue · 2 comments
Deleted user commented
Describe the Bug
The keras callback ReduceLROnPlateau, expects a property called "lr" for the learning rate of the optimiser. RAdam does not appear to have this? (also, the parameter is called learning_rate? where normally it would be just lr)
Deleted user commented
(btw, you implemented RAdam super fast! Nice! 👍 )
CyberZHG commented
The base optimizer is copied from the tf-2 branch of keras. I've changed the name to lr.