Availability of testset 1 labels

Hello,

For round 2: since testset 2 (the testset of round 2) is near to the trainset and testset 1, adding testset 1 data in training would probably help to improve the model performance. However, we do not have testset 1 labels. If one wants to use trainset + testset 1 in training, he should first train a good “round 1” model. This means that if someone wants to succeed in round 2, his round 1 model needs to be the best (or among the bests).

My question is: do you plan to release the ground-truth of testset 1, so that round 2 becomes independent of round 1?

Thank you in advance for your answer.

View post 0

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

Thank you very much!

View post 0

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!

View post 0