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
What I understood is that the author has said the weight parameter will be used to compute the total loss. But when the updation of the centers is being done it is being done without the weight parameter.
Basically, the updates for the centers in this code is nothing but the backpropagation of the mean square error loss.
Congratuations! You have done a great work. But I have a question about the center loss.
Can you explain why you wrote there two lines?
pytorch-center-loss/main.py
Line 128 in 082ffa2
Thank you very much! Looking forward to your reply!
The text was updated successfully, but these errors were encountered: