You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I read the paper and try to understand the model in train_val.prototxt .
As far as i know, final1 & final2 are both ranking functions, and labelr produces labels of {-1, 1}, then the ranking_loss is EuclideanLoss((final1 - final2) * labelr, 0)
my question is:
For me, EuclideanLoss((final1 - final2) * labelr, 0) is quite strange, because labelr seems to be useless in this loss function.
EuclideanLoss((final1 - final2) * labelr, 0) is quite different from the loss function in paper, which i think is like [ max(0, (final1 - final2) * labelr) ]^2.
For both of the above loss function, I think gradient vanishing will occur during training, because both final1 and final2 could be very small(say 1.1e-5, 1.2e-5), and the loss will be very small. Is that the case?
Did i miss something important?
Looking forward to your reply. Thanks again.
The text was updated successfully, but these errors were encountered:
Hi, thank you for your paper and code.
I read the paper and try to understand the model in
train_val.prototxt
.As far as i know,
final1
&final2
are both ranking functions, andlabelr
produces labels of {-1, 1}, then the ranking_loss isEuclideanLoss((final1 - final2) * labelr, 0)
my question is:
EuclideanLoss((final1 - final2) * labelr, 0)
is quite strange, becauselabelr
seems to be useless in this loss function.EuclideanLoss((final1 - final2) * labelr, 0)
is quite different from the loss function in paper, which i think is like[ max(0, (final1 - final2) * labelr) ]^2
.Did i miss something important?
Looking forward to your reply. Thanks again.
The text was updated successfully, but these errors were encountered: