Macro Recall

Problem

Compute macro-averaged recall over num_classes.

Class recall is the number of correct predictions for that class divided by the number of target pixels of that class; classes with no target pixels count as 0.0. Return the unweighted mean rounded to 4 decimal places.

Test cases

case 1

in: [[[0,1],[2,1]],[[0,1],[2,0]],3]

expected: 0.8333

case 2

in: [[[0,0]],[[1,1]],2]

expected: 0

case 3

in: [[[1,0]],[[1,1]],2]

expected: 0.25

Starter codePython

def macro_recall(pred, target, num_classes):
    # Your code here
    pass

3 test cases · run your code against them in the editor