search

qiuqiangkong / audioset_tagging_cnn

MIT License
1.32k stars 249 forks source link

Binarizing output values #41

Open anarsultani97 opened 3 years ago

anarsultani97 commented 3 years ago

Hi Qiuqiang,

I would like to know what is the best way to binarize the linear predicted probabilities in a way that :

If you have any suggestion for binarization issue , it would be great to know it.

And one more question about clipwise_output , as I understood from the paper linear probability value for each label shows the presence of that audio label in the input audio and probability value doesn't depend on the duration of period of audio label happens. I mean if it happens during the very short duration or long duration. Am I right?

It would be great for me to get your answers for above mentioned questions.

Anar Sultani

qiuqiangkong commented 3 years ago

To binarize the results, the easiest way is to use a threshold of 0.3. The prediction probability will not be affected by the duration of audio. Even if a sound event has a short duration, the predicted probability should be large.