Validation loss not decreasing

That probably doesn’t what you think it does.

Some things you could look at / share for debugging

  • What’s the imbalance between the classes? What’s happening? Does the net always predict a large class? Generally, looking at per-class accuracies / the confusion matrix is a good idea.
  • I would usually try to modify the dataset to give the classes an equal number of times by duplicating the minority classes. Similar to here: Multiclass classification: Skewed data problem and labeling

Best regards

Thomas