Inconsistency between the relative throughput and R2 calculation. #6284
Unanswered
kohankhaki
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
In the cost model, the training targets are the relative throughput within each batch. But to calculate R2 score, the rankings should be calculated based on the network's output for the whole dataset. So the is a consistency between what is required by R2 and what does the network output. Does anyone have any idea about this? Is there something that I am missing?
Beta Was this translation helpful? Give feedback.
All reactions