siamese_tf_mnist icon indicating copy to clipboard operation
siamese_tf_mnist copied to clipboard

Definition of loss seems incorrect

Open kartikpaigwar opened this issue 7 years ago • 0 comments

Negative loss should be equal to (1-label)*ecud2. Also respective change should be made in possitive loss. For exact equation see about contrastive loss

kartikpaigwar avatar Jan 10 '18 11:01 kartikpaigwar