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
Hi Maxim Berman! Great Work.
I am using the lovasz_hinge loss and iou_binary as my metric.
My labels are binary masks of foreground represented as 1 and background as 0.
And I am currently overfitting one example just to see how my model(which is a form of hyper-network) works.
But as the Lovasz Hinge loss decreases, the output of iou_binary also decreases.
Thanks alot in advance for helping
The text was updated successfully, but these errors were encountered:
Hello,
Because Lovász-hinge/softmax are relaxations it is unfortunately not always the case that decreasing them is directly correlated with increasing IoU. You could test if Lovász-sigmoid (2D version of Lovász-Softmax) performs better than Lovász-Hinge for your application.
Hi Maxim Berman! Great Work.
I am using the lovasz_hinge loss and iou_binary as my metric.
My labels are binary masks of foreground represented as 1 and background as 0.
And I am currently overfitting one example just to see how my model(which is a form of hyper-network) works.
But as the Lovasz Hinge loss decreases, the output of iou_binary also decreases.
Thanks alot in advance for helping
The text was updated successfully, but these errors were encountered: