Any way to access the loss function within a optimizer? #19823
Unanswered
Ethan74884
asked this question in
Q&A
Replies: 1 comment
-
What does that mean? Usually, the loss function is a function that measures the loss value through the output of the model and actual output and compares their distance in an abstract sense. You can calculate the loss value during parameter update or after updating the parameters too. In that cases, you might have to write your own custom loops. This is my understanding. Best Regards. |
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 am trying to implement an idea I had for a optimizer, but it requires calculating the loss during the parameter update, Google has nothing and looking and I failed to find any documentation about such a possibility, any way to do it?
Beta Was this translation helpful? Give feedback.
All reactions