News for hackers. Stuff that matters.
Re:A Recipe for Training Neural Networks by snrji on Friday April 26, 2019 @03:37AM (#19755497)
By "eval" you can also mean the training subset. As I understood is at the code to evaluate the network at a given point with a given dataset. For instance, after epoch epoch, the model is evaluated for both training and validation (you see both losses)

As you said, the test subset should only be used at the very last.

There are no comments on this comment yet.