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
As far as I understtod, your code supports only a binary classification problem. I could not find any information in the paper regarding the classes (the "Words"/"Subjects" are the classes?). I am trying to use this for a multi-class problem. Since pairing has been done for frame sequences of each video (9 of them) with the corresponding speech spectrogram and MFEC features, I suppose there will be no problem if one changes the number of classes.
When I change number of classes from 2 to 6, I get this error, can you help me?
Is this because of ROC calculation (line 659 of train.py) for multi-class classification? Can you tell me which parts need modification, maybe I missed something.
The text was updated successfully, but these errors were encountered:
The paper is for verification. It only deals with binary classification as a consequence.
I do not understand what you meant about class definition. The point is when you create pairs for comparison, it is a binary classification problem. No matter who is saying what. So the subject and the spoken words do not matter.
Please read the associated paper for further details.
@asinatorfi I understand that this is a verification paper for binary classification. I already changed the metrics and my problem is solved. Sorry, I forgot to close the issue. Thanks a lot for your helps.
As far as I understtod, your code supports only a binary classification problem. I could not find any information in the paper regarding the classes (the "Words"/"Subjects" are the classes?). I am trying to use this for a multi-class problem. Since pairing has been done for frame sequences of each video (9 of them) with the corresponding speech spectrogram and MFEC features, I suppose there will be no problem if one changes the number of classes.
When I change number of classes from 2 to 6, I get this error, can you help me?
Is this because of ROC calculation (line 659 of train.py) for multi-class classification? Can you tell me which parts need modification, maybe I missed something.
The text was updated successfully, but these errors were encountered: