FPN Lateral 1x1

Problem

Apply a 1x1 lateral convolution implemented as per-channel scaling.

Multiply channel c of every pixel by scales[c] and round to 4 decimal places.

case 1

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

expected: [[[2,6],[6,12]]]

case 2

in: [[[[10,0,5]]],[0.5,2,1]]

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

case 3

in: [[[[1,2],[3,4]]],[1,0]]

expected: [[[1,0],[3,0]]]

Starter codePython

def lateral_scale(feature, scales):
    # Your code here
    pass

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