Which average method is used in the calculation of f1-score?

Hello,

If I understand correctly, the principle evaluation method is multi-class f1-score. I would like to ask which average method is used in the calculation of this f1-score? For example, if we use sklearn.metrics.f1_score, there are options of ‘micro’, ‘macro’ or ‘weighted’.

If someone knows the answer, that would help me a lot.

Thank you very much!

From the discord, @mohanty said it’s macro. But they might change it to weighted maybe in the 2nd round.
cmiiw

Thank you very much!