Macro Multiclass Dice

Problem

Compute the macro-averaged Dice coefficient over classes.

For each class Dice = 2 * intersection / (predicted + target), counted over pixels; classes whose denominator is zero are skipped. Return the mean over the remaining classes rounded to 4 decimal places, or 0.0 when every class is empty.

Test cases

case 1

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

expected: 1

case 2

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

expected: 0.5

case 3

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

expected: 1

Starter codePython

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

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