sharib-vision/EAD2019

Question of F2-score

Closed this issue · 1 comments

The new metric F2-score is released. However, I am confused of it.
According to the code, we need to have the 'confusion_matrix' to get 'fp, tp and fn'. If the input of 'prediction and ground_truth' is of 5 channels, how to define the label of each channel? If the labels the 5 classes are defined as 255 while the backgrounds are 0, the 'confusion_matrix' is not right because only the bins of 0 and 1 have values.
As as result, I guess the confusion_matrix should be based on a single channel and the 'nr_labels' should be 2.
Thanks for your attention!

Hi,

thank you for your observation. We have checked it and fixed the bug.
We have uploaded the method and its available to be used for leaderboard scoring.

Best,