deep-learning-for-indentation icon indicating copy to clipboard operation
deep-learning-for-indentation copied to clipboard

Published 20 hours ago • verified publisher icon lululxvi

How "training loss" ""test loss" and "test metric" are defined?

Open qjiao1 opened this issue 2 years ago • 1 comments

Would you please explain how the "training loss" ""test loss" and "test metric" are defined? I'm not sure why there are two values associated with training/test loss. image

qjiao1 avatar Sep 29 '21 20:09 qjiao1

"loss" is the loss you defined to train the network. Two values means there are more than one loss terms. Not sure what code you used, but it seems that the second value is the regularization loss.

Metric is the metirc you defined in your code.

lululxvi avatar Oct 07 '21 02:10 lululxvi