top | item 28753943

(no title)

hchasestevens | 4 years ago

Surely they must have already established a loss function in order to train the network in the first place?

discuss

order

whimsicalism|4 years ago

Sometimes the metric you use for the loss function is not the best metric for eval. Think BLEU for translation, for instance (not that BLEU is particularly great).