0

I am working on multilabel classification problem. The classes are highly imbalance. However, I balanced the imbalance problem with class weights. I am using "Binary cross entropy" as cost funtion and sigmoid activation function at output layer. But, I am confused with loss curve (since the validation loss and testing loss are parallel ). Is this the case of overfitting?

enter image description here

desertnaut
  • 57,590
  • 26
  • 140
  • 166
Aman Agarwal
  • 3
  • 1
  • Yes, It is a 12 class multilabel classification problem, in which one class contains 4096 (class with highest instance ) instances, one of the other class contains 76 (class with lowest instance) instances, and other classes contain instances between 76 to 4096. – Aman Agarwal Mar 14 '19 at 10:34

1 Answers1

0

The telltale signature of overfitting is when your validation loss starts increasing, while your training loss continues decreasing, i.e.:

adapted from Wikipedia

(Image adapted from Wikipedia entry on overfitting)

Here are some other plots indicating overfitting (source):

enter image description here

enter image description here

See also the SO thread How to know if underfitting or overfitting is occuring?.

Clearly, your plot does not exhibit such behavior, hence you are not overfitting.

desertnaut
  • 57,590
  • 26
  • 140
  • 166