Random Erasing

Problem

Erase a random square region of an image with a seeded RNG.

Seed the random module; the square side is max(1, round(sqrt(area_frac * H * W))) clipped to the image, the top-left is uniform in the remaining range, and the region is filled with 0.

Test cases

case 1

in: [[[5,5,5,5],[5,5,5,5],[5,5,5,5],[5,5,5,5]],0.25,2]

expected: [[0,0,5,5],[0,0,5,5],[5,5,5,5],[5,5,5,5]]

case 2

in: [[[5,5,5,5],[5,5,5,5],[5,5,5,5],[5,5,5,5]],0.1,0]

expected: [[5,5,5,5],[5,5,5,5],[5,5,5,5],[5,5,5,0]]

case 3

in: [[[1,2],[3,4]],0.5,1]

expected: [[0,2],[3,4]]

case 4

in: [[[1,2,3],[4,5,6],[7,8,9]],1,0]

expected: [[0,0,0],[0,0,0],[0,0,0]]

Starter codePython

def random_erasing(image, area_frac, seed):
    # Your code here
    pass

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